© 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. 14467
    Prev
    Next
    INDEX
    Explanations

    mentions of government organizations and institutes, especially those involving textiles and technology

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

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

    various 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_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
    QMetaType
    -0.57
    ագրություններ
    -0.57
    RenderAtEndOf
    -0.54
    PYX
    -0.52
     digitais
    -0.49
     zamanda
    -0.48
    TypedDataSet
    -0.48
     StatefulWidget
    -0.48
    rungsseite
    -0.47
     dieną
    -0.47
    POSITIVE LOGITS
    ioi
    0.59
    uci
    0.57
    ürlich
    0.56
    oi
    0.56
    DebuggerNonUser
    0.55
    %");
    0.55
     <>",
    0.54
    tal
    0.53
    dorf
    0.53
    LookAnd
    0.52
    Activations Density 0.677%

    No Known Activations