© 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. 27305
    Prev
    Next
    INDEX
    Explanations

    features and control

    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
    動画
    0.40
     புத்தக
    0.40
    絃
    0.39
    devDependencies
    0.38
     動画
    0.38
    (**
    0.37
     അവര്‍
    0.37
    หนังสือ
    0.37
    小説
    0.37
    팀
    0.36
    POSITIVE LOGITS
     leb
    0.45
     increment
    0.41
     pamo
    0.41
     incremento
    0.39
    বরা
    0.38
     incrementar
    0.37
    increment
    0.37
    ಕ್ರ
    0.35
     concatenated
    0.35
     жи
    0.35
    Activations Density 0.000%

    No Known Activations