© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15735
    Prev
    Next
    INDEX
    Explanations

    strings of abstract words, some of which are related to philosophy or politics

    oai_token-act-pair · gemini-2.0-flash

    cold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.00
    '
    -0.72
    ↵↵
    -0.71
    setVerticalGroup
    -0.64
    Personensuche
    -0.60
    անում
    -0.57
     OFDb
    -0.55
    rrggbb
    -0.54
    sizeCache
    -0.54
     beginnetje
    -0.53
    POSITIVE LOGITS
     ſeveral
    0.72
     reaſon
    0.71
     Majefty
    0.70
     purpoſe
    0.70
     leaſt
    0.70
     leſs
    0.68
     belangrij
    0.68
     laſt
    0.67
     whoſe
    0.66
     useStyles
    0.65
    Activations Density 0.151%

    No Known Activations