© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32423
    Prev
    Next
    INDEX
    Explanations

    formulas and calculations

    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
    HeightSizeMode
    0.39
     curiosity
    0.38
     kms
    0.37
    achtet
    0.36
     Curious
    0.36
     höchste
    0.35
     gacchati
    0.35
    ᆻ
    0.35
    StatusOK
    0.35
     cocktail
    0.34
    POSITIVE LOGITS
    十一章
    0.52
     Cardiol
    0.39
     Huck
    0.37
     supplic
    0.37
     ‘‘
    0.37
    routed
    0.37
    viable
    0.37
    Phot
    0.36
    ‘‘
    0.35
     डेली
    0.35
    Activations Density 0.003%

    No Known Activations