© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16090
    Prev
    Next
    INDEX
    Explanations

    words which can indicate scientific or medical discussions of facts and observations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     riten
    -0.57
    ніципалі
    -0.52
     façons
    -0.51
     impacting
    -0.49
    ัติ
    -0.49
    НИК
    -0.47
     virtuel
    -0.45
    }$_
    -0.45
    лару
    -0.44
     препратки
    -0.44
    POSITIVE LOGITS
    ngdoc
    0.69
    InjectAttribute
    0.64
    SequentialGroup
    0.63
     Signalez
    0.58
    BagLayout
    0.57
    contentLoaded
    0.56
    windowFixed
    0.56
    期刊论文
    0.55
    +:+
    0.54
    vised
    0.53
    Activations Density 7.905%

    No Known Activations