© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246556
    Prev
    Next
    INDEX
    Explanations

    Ann Pat, Ann Nap, Annals

    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
     Cinemas
    0.39
     jammed
    0.38
    ರೇ
    0.38
    剌
    0.37
    Bet
    0.37
    MaxPooling
    0.37
    Ô
    0.36
    鋆
    0.36
     Crisis
    0.35
    Crisis
    0.35
    POSITIVE LOGITS
     純正
    0.38
    摧
    0.37
    غط
    0.36
     চ্যানে
    0.36
     استاذ
    0.36
    ক্তার
    0.36
    izhou
    0.35
     chains
    0.35
     عل
    0.34
     პარ
    0.34
    Activations Density 0.023%

    No Known Activations