© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2655
    Prev
    Next
    INDEX
    Explanations

    code snippets containing certain keywords such as "expect", "info","trials", "MutableArray", and "Object".

    oai_token-act-pair · gemini-2.0-flash

    unusual or undefined token patterns

    np_token-act-pair-logits · gpt-4o-mini

    Technical/code snippets

    np_max-act-logits · gemini-2.0-flash

    info

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.46
     Efq
    -0.45
    ^(@)
    -0.43
     Majefty
    -0.42
     myſelf
    -0.40
     becauſe
    -0.38
     Monfieur
    -0.37
     themſelves
    -0.36
     himſelf
    -0.36
     Jefus
    -0.36
    POSITIVE LOGITS
    <bos>
    0.83
    gel
    0.29
     VIDEOTAPE
    0.28
    ρυ
    0.28
    vor
    0.27
    ро
    0.27
    нен
    0.27
    fa
    0.27
    od
    0.27
    <eos>
    0.26
    Activations Density 60.506%

    No Known Activations