© 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. 12240
    Prev
    Next
    INDEX
    Explanations

    source code filepaths and diff markup

    oai_token-act-pair · gemini-2.0-flash

    say "/"

    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
     purpoſe
    -0.82
     ſever
    -0.73
     Reſ
    -0.68
     uſed
    -0.68
     againſt
    -0.68
     myſelf
    -0.65
     Cæsar
    -0.65
     fevere
    -0.64
     Púb
    -0.63
     perſon
    -0.63
    POSITIVE LOGITS
     /\.(
    0.71
    !
    0.63
     }?>
    0.63
    /
    0.62
    (!__
    0.60
    ($__
    0.57
    ↵↵
    0.57
    ::*;
    0.57
    ver
    0.56
    ngdoc
    0.56
    Activations Density 3.354%

    No Known Activations