© 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. 7615
    Prev
    Next
    INDEX
    Explanations

    text from multiple internet forums, code snippets, and documentation concatenated together.

    oai_token-act-pair · gemini-2.0-flash

    programming syntax or keywords

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

    period

    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
    unkel
    -0.54
    以來
    -0.53
    mehl
    -0.53
    /'+
    -0.52
    kante
    -0.52
    以来
    -0.51
    machi
    -0.51
    kret
    -0.50
    nologie
    -0.50
     end
    -0.49
    POSITIVE LOGITS
    PreferredItem
    0.69
    styleUrls
    0.67
     transférez
    0.65
     itſelf
    0.64
    ]")]
    0.64
    basicConfig
    0.63
    出版年
    0.62
     defaultstate
    0.61
     myſelf
    0.60
    InputBorder
    0.60
    Activations Density 4.408%

    No Known Activations