© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 78181
    Prev
    Next
    INDEX
    Explanations

    jumping between gaps

    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
    逃
    0.39
    steiner
    0.38
    苯
    0.37
    शाला
    0.35
     সংগ্রহের
    0.35
    stool
    0.34
    襁
    0.34
    consin
    0.34
    emaakt
    0.34
     algod
    0.34
    POSITIVE LOGITS
     penetrated
    0.40
    読
    0.38
    페
    0.37
     проник
    0.37
     reading
    0.36
    namespaces
    0.36
    libs
    0.36
     penetration
    0.35
     penetrating
    0.35
    endant
    0.34
    Activations Density 0.001%

    No Known Activations