© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10534
    Prev
    Next
    INDEX
    Explanations

    format, schema, compare, delay, clamp, fit, loop

    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
    setId
    0.40
     sett
    0.38
     dynamique
    0.36
     settlement
    0.35
     settle
    0.35
     zoo
    0.34
    덥
    0.34
     слово
    0.34
     Iterable
    0.34
     tirelessly
    0.34
    POSITIVE LOGITS
    மைக்
    0.44
    夂
    0.41
    As
    0.39
    astikan
    0.39
    中部
    0.39
    JTextField
    0.39
     phys
    0.38
    AsString
    0.38
    astype
    0.37
    OLDER
    0.37
    Activations Density 0.071%

    No Known Activations