© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8135
    Prev
    Next
    INDEX
    Explanations

    always coming

    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_40_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
     стиля
    0.51
    风格
    0.44
     стиле
    0.44
     estilo
    0.43
    éristique
    0.43
     estilos
    0.42
    風格
    0.42
    宝
    0.41
    椁
    0.41
     शैली
    0.41
    POSITIVE LOGITS
     sag
    0.37
     devise
    0.36
     이어
    0.35
    checked
    0.35
     breakaway
    0.35
     Mechanical
    0.34
     mechanics
    0.34
    teams
    0.34
     tins
    0.34
     prep
    0.34
    Activations Density 0.000%

    No Known Activations