© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163092
    Prev
    Next
    INDEX
    Explanations

    GUI/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    แล
    0.31
    From
    0.31
    商
    0.30
     сиг
    0.30
     state
    0.29
    ID
    0.28
    state
    0.28
    Від
    0.28
     writes
    0.28
    夕
    0.27
    POSITIVE LOGITS
     documentación
    0.40
    pessoas
    0.36
     fotos
    0.33
     actualidad
    0.33
     Palma
    0.33
     foto
    0.33
     documenting
    0.33
     Documentation
    0.32
    Constraint
    0.32
     இடத்தை
    0.32
    Activations Density 0.000%

    No Known Activations