© 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. 76370
    Prev
    Next
    INDEX
    Explanations

    onSubmit handler assignment

    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
    idamente
    0.39
    ReactDOM
    0.39
    हुन्छ
    0.39
     ನಾಗ
    0.38
     gimana
    0.38
     אטאטורק
    0.38
    캅
    0.37
     ಹೇಗೆ
    0.37
    maq
    0.37
    ProductName
    0.37
    POSITIVE LOGITS
     ek
    0.42
     =
    0.41
     read
    0.40
     alt
    0.40
     Laurent
    0.40
    =
    0.40
     abort
    0.39
    el
    0.38
     Dub
    0.37
    e
    0.37
    Activations Density 0.000%

    No Known Activations