© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164654
    Prev
    Next
    INDEX
    Explanations

    organic molecules and life's origins

    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_13_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
    P
    0.33
    Region
    0.31
    ゾーン
    0.30
    Developers
    0.30
    FI
    0.29
    ש
    0.29
    トレンド
    0.29
    Α
    0.29
    FF
    0.29
    Strategy
    0.28
    POSITIVE LOGITS
     amines
    0.35
     operas
    0.34
    lexeme
    0.31
     зару
    0.30
     lexical
    0.30
     adren
    0.30
     ofrecer
    0.30
     inconsc
    0.30
     Carlyle
    0.30
     одежда
    0.30
    Activations Density 0.005%

    No Known Activations