© 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. 163794
    Prev
    Next
    INDEX
    Explanations

    gameplay effects and modifiers

    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
     పే
    0.41
    ଖ
    0.39
     समन्व
    0.38
     profitable
    0.38
     marina
    0.37
    pathname
    0.37
     SNPs
    0.37
     FINANCIAL
    0.37
     easy
    0.36
    opensource
    0.36
    POSITIVE LOGITS
    KBr
    0.36
    弗
    0.36
    धिकारियों
    0.35
    ">+
    0.35
     wield
    0.35
     spectator
    0.35
    Duration
    0.34
    ꒷
    0.34
    radial
    0.34
     తగ్గి
    0.33
    Activations Density 0.005%

    No Known Activations