© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 267
    Prev
    Next
    INDEX
    Explanations

    mentions of the reader or author, as well as invitations to engage

    oai_token-act-pair · gemini-2.0-flash

    let's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Autoritní
    -0.63
    gameserver
    -0.52
    MetaObject
    -0.48
     Italij
    -0.47
    consulté
    -0.47
     autorytatywna
    -0.46
    usiai
    -0.46
     obiet
    -0.46
     Houſe
    -0.45
     الحره
    -0.44
    POSITIVE LOGITS
    enumi
    0.85
    \{\\
    0.65
    })).
    0.61
    enumii
    0.59
    RTLR
    0.58
    }`).
    0.58
    WireFormatLite
    0.54
    }')
    0.54
    }));
    0.53
    ranton
    0.51
    Activations Density 11.421%

    No Known Activations