© 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. 33013
    Prev
    Next
    INDEX
    Explanations

    magic, database, api keys

    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
     sistema
    0.39
    డ
    0.38
     tend
    0.37
    ระบบ
    0.37
     దో
    0.36
    과학
    0.36
    🥜
    0.36
     과학
    0.35
    system
    0.35
     ګټ
    0.35
    POSITIVE LOGITS
     patron
    0.46
     Patron
    0.42
     patrons
    0.39
    월
    0.38
    anoate
    0.36
    বী
    0.36
     subclass
    0.36
     Intr
    0.36
     สื
    0.36
    লেট
    0.36
    Activations Density 0.099%

    No Known Activations