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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6465
    Prev
    Next
    INDEX
    Explanations

    conversation especially quotes

    oai_token-act-pair · gemini-2.0-flash

    unusual or non-standard text formats

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

    Code snippets and errors

    np_max-act-logits · gemini-2.0-flash
    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
    nmgp
    -0.39
    j
    -0.38
    ack
    -0.35
    RTRS
    -0.35
     open
    -0.35
     taha
    -0.35
     F
    -0.35
     Pols
    -0.35
     even
    -0.34
     ولاية
    -0.34
    POSITIVE LOGITS
    ])));
    0.88
     Efq
    0.87
    WebVitals
    0.85
     itſelf
    0.84
     MainAxisSize
    0.84
     Diſ
    0.84
    principalTable
    0.83
     ſtate
    0.81
    Erreferentziak
    0.81
    AndEndTag
    0.80
    Activations Density 5.528%

    No Known Activations