© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13273
    Prev
    Next
    INDEX
    Explanations

    file paths or URLs containing directory separators

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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>
    -0.82
    AddTagHelper
    -0.75
    AndEndTag
    -0.67
    GraphicsUnit
    -0.65
    ⓧ
    -0.61
     muualla
    -0.60
    MLLoader
    -0.60
    findpost
    -0.60
     MainAxisSize
    -0.60
    Cursors
    -0.58
    POSITIVE LOGITS
    ckets
    0.56
    发表于
    0.56
    dAtA
    0.51
    lán
    0.48
    ofre
    0.47
    泛
    0.46
    tacles
    0.45
    igh
    0.45
     last
    0.44
     continent
    0.43
    Activations Density 1.237%

    No Known Activations