© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    nocode, noclipping, nociceptors

    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
     ఉద్య
    0.40
    ('$(
    0.37
     Lloyd
    0.37
     পুস্তকের
    0.36
     صور
    0.36
    ᐸ
    0.36
    那个
    0.35
     번
    0.35
    _${
    0.34
    ($(
    0.34
    POSITIVE LOGITS
     ValueTask
    0.40
     privé
    0.37
     Mone
    0.37
    ვ
    0.37
    Info
    0.37
    lf
    0.36
    Bold
    0.36
     Bringing
    0.36
    Pri
    0.36
     entrop
    0.36
    Activations Density 0.000%

    No Known Activations