© 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. 74995
    Prev
    Next
    INDEX
    Explanations

    API keys and message handling

    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
     السما
    0.40
    柾
    0.40
    nisse
    0.38
     provas
    0.38
    Joshua
    0.37
    諺
    0.36
    ModelComponent
    0.36
    BANNER
    0.36
    恝
    0.36
     pred
    0.35
    POSITIVE LOGITS
    itare
    0.37
     Combo
    0.33
    차
    0.32
     pét
    0.32
     Buckingham
    0.31
     combos
    0.31
     extinguishing
    0.31
    വ്ര
    0.31
    firing
    0.31
    原材料
    0.31
    Activations Density 0.000%

    No Known Activations