© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14309
    Prev
    Next
    INDEX
    Explanations

    words related to scores, amounts, and performance in games, elections, and academic standing

    oai_token-act-pair · gemini-2.0-flash

    Scoring/points

    np_max-act · 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
     متعلقه
    -0.56
    IMPORTED
    -0.50
    дзе
    -0.47
     indisponible
    -0.47
    #+#
    -0.46
     happy
    -0.45
    覚
    -0.45
     happier
    -0.44
    +#+#
    -0.44
     gewe
    -0.43
    POSITIVE LOGITS
    <bos>
    0.77
    CloseOperation
    0.66
    ReusableCell
    0.64
     scored
    0.63
     scores
    0.59
    WebElementEntity
    0.59
     tallied
    0.57
     score
    0.56
     tally
    0.56
     дописавши
    0.54
    Activations Density 2.082%

    No Known Activations