© 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. 7910
    Prev
    Next
    INDEX
    Explanations

    descriptions of systems working

    oai_token-act-pair · gemini-2.0-flash

    expressions of successful functioning or effectiveness

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

    work

    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
    ftagPool
    -0.72
    новниш
    -0.65
    dafx
    -0.58
     ModelExpression
    -0.57
    }{*}{
    -0.57
     CWE
    -0.57
    flink
    -0.55
    bilirsiniz
    -0.55
    ceptar
    -0.54
     متعلقه
    -0.54
    POSITIVE LOGITS
     aloud
    0.48
    ViewFeatures
    0.47
     posthum
    0.47
     restTemplate
    0.46
     trå
    0.45
    endif
    0.45
     juu
    0.44
     automaticamente
    0.43
     Autorisations
    0.43
    TokenName
    0.43
    Activations Density 4.732%

    No Known Activations