© 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. 33040
    Prev
    Next
    INDEX
    Explanations

    jetpack compose

    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
    ioane
    0.40
     रेटिंग
    0.40
    ratings
    0.39
     //</
    0.39
     مط
    0.39
    Hace
    0.39
    Amplitude
    0.39
    Tras
    0.38
    Verse
    0.38
    ]={"
    0.38
    POSITIVE LOGITS
     sli
    0.39
    ELD
    0.39
     kite
    0.38
     ${
    0.38
    orsa
    0.38
     हर्ष
    0.38
    ගත
    0.36
     source
    0.36
    olson
    0.36
     Poles
    0.36
    Activations Density 0.002%

    No Known Activations