© 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. 80381
    Prev
    Next
    INDEX
    Explanations

    `out=` assignments

    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
    ('/\
    0.44
    ht
    0.37
    дня
    0.37
     harshly
    0.35
    гно
    0.35
     Mat
    0.34
     malfunctions
    0.34
    cenie
    0.33
    ArrivalTime
    0.32
     phot
    0.32
    POSITIVE LOGITS
     Attention
    0.36
     Consideration
    0.36
    ಫ
    0.35
     தொற்று
    0.35
    有意
    0.35
     embal
    0.35
    恜
    0.35
     quedaría
    0.35
    inches
    0.35
     以下
    0.35
    Activations Density 0.000%

    No Known Activations