© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119894
    Prev
    Next
    INDEX
    Explanations

    cosmic horror investigators

    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_38_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
     Transparent
    0.40
    OnOff
    0.38
    ysta
    0.35
    inel
    0.35
     заво
    0.35
    情人
    0.35
     objekt
    0.35
    ڃ
    0.34
     transparent
    0.34
     nieruch
    0.34
    POSITIVE LOGITS
     $("#"
    0.43
    Keeper
    0.41
     substitutions
    0.40
     investigator
    0.39
     outer
    0.39
     Inns
    0.39
    Ark
    0.38
     cyclic
    0.38
     Ark
    0.38
     reagent
    0.38
    Activations Density 0.030%

    No Known Activations