© 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. 162701
    Prev
    Next
    INDEX
    Explanations

    mostly

    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
    唥
    0.46
     어디
    0.42
    compliance
    0.40
    להקה
    0.40
    ⇜
    0.39
    लखनऊ
    0.38
    იზ
    0.38
    pageNum
    0.38
    ...');
    0.37
    )–
    0.37
    POSITIVE LOGITS
    ップ
    0.38
     योग
    0.37
    ப்படுகிறது
    0.37
     многи
    0.36
    Kp
    0.35
     grandes
    0.35
     consider
    0.33
     huge
    0.33
    anga
    0.33
     Spinal
    0.33
    Activations Density 0.004%

    No Known Activations