© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5558
    Prev
    Next
    INDEX
    Explanations

    capitalized words, especially those that could be names or places

    oai_token-act-pair · gemini-2.0-flash

    Random text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    <eos>
    -0.49
    <0xE8>
    -0.42
    ми
    -0.37
    for
    -0.37
    <0xE7>
    -0.36
    rm
    -0.35
    mit
    -0.35
    <u>
    -0.35
    ila
    -0.34
    ...
    -0.34
    POSITIVE LOGITS
    ^(@)
    1.79
     Efq
    1.75
     doubtnut
    1.59
     Forumite
    1.46
     Majefty
    1.45
     photolibrary
    1.43
    drawal
    1.41
    LookAnd
    1.40
    olesale
    1.40
    ſelf
    1.39
    Activations Density 8.384%

    No Known Activations