© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10431
    Prev
    Next
    INDEX
    Explanations

    reviews of restaurants, including both glowing praise and harsh criticism.

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Portale
    -0.71
    expandindo
    -0.64
    VIAF
    -0.63
    Portály
    -0.57
    MigrationBuilder
    -0.56
    KeySpec
    -0.55
     geslacht
    -0.55
    رشف
    -0.53
    ंदीखरीदारी
    -0.52
    ベーション
    -0.51
    POSITIVE LOGITS
     Gegenteil
    0.58
    DoubleQuotes
    0.52
    Становништво
    0.50
     уго
    0.50
    zies
    0.47
    큼
    0.47
     vastu
    0.44
     acety
    0.44
    appé
    0.44
    xer
    0.44
    Activations Density 1.435%

    No Known Activations