© 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-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197687
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     USC
    0.47
     a
    0.45
     the
    0.45
     Freud
    0.45
     South
    0.42
    NAMEN
    0.42
     DESC
    0.41
     praised
    0.41
     e
    0.41
    Earth
    0.41
    POSITIVE LOGITS
    équation
    0.58
    tt
    0.57
     essentiellement
    0.54
    น
    0.53
    𝖐
    0.47
    ث
    0.46
     manfaat
    0.46
     игро
    0.46
     salariés
    0.46
     xxl
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.