© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8348
    Prev
    Next
    INDEX
    Explanations

    parts of a conversation between two people

    oai_token-act-pair · gemini-2.0-flash

    Quotations and dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     iyon
    -0.49
    Cordialement
    -0.46
    Итак
    -0.45
    佬
    -0.44
    unct
    -0.41
    offsetWidth
    -0.40
     Joaquin
    -0.40
    RND
    -0.40
     offend
    -0.40
    jre
    -0.40
    POSITIVE LOGITS
    ValueStyle
    1.06
    MigrationBuilder
    0.89
     дописавши
    0.88
     CreateTagHelper
    0.85
     ModelExpression
    0.81
    IntoConstraints
    0.79
     يتيمه
    0.77
    Билгалдахарш
    0.77
    tagHelperRunner
    0.75
    homonymie
    0.75
    Activations Density 0.339%

    No Known Activations