© 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. 15274
    Prev
    Next
    INDEX
    Explanations

    words and phrases in a diverse mix of texts with a slightly positive or neutral tone, including discussions, politics, law, sports, and technology.

    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
     itſelf
    -0.91
     ModelExpression
    -0.85
     חיצוניים
    -0.84
     myſelf
    -0.77
    ंदीखरीदारी
    -0.76
    <bos>
    -0.73
    المكان
    -0.71
     purpoſe
    -0.66
     consultato
    -0.65
     themſelves
    -0.65
    POSITIVE LOGITS
    ATIVO
    0.42
    /(
    0.40
     входит
    0.38
     Eigentum
    0.38
     lenker
    0.37
    umbar
    0.37
    ęty
    0.37
    meli
    0.37
    /<
    0.36
    Notae
    0.36
    Activations Density 33.740%

    No Known Activations