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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3697
    Prev
    Next
    INDEX
    Explanations

    mentions of awards

    oai_token-act-pair · gemini-2.0-flash

    Awards ceremonies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PHeader
    -0.57
    `,
    -0.56
     >=",
    -0.56
    AutoresizingMask
    -0.55
    ])):
    -0.55
    tagHelperRunner
    -0.54
    ngdoc
    -0.54
    SourceChecksum
    -0.54
    abetes
    -0.53
    //
    -0.53
    POSITIVE LOGITS
    balleur
    0.52
    defaultProps
    0.51
    zeera
    0.51
    SerializedSize
    0.50
     Britton
    0.49
    StructEnd
    0.48
    ViewType
    0.46
     ryt
    0.45
     Almeida
    0.45
     bey
    0.44
    Activations Density 10.836%

    No Known Activations