© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207086
    Prev
    Next
    INDEX
    Explanations

    20th/21st century music composers

    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_20_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
     doorways
    0.45
     टिकट
    0.45
    岩
    0.44
     venues
    0.44
    сал
    0.43
    คาร
    0.42
     empowerment
    0.42
    犊
    0.42
    建築
    0.41
     chairs
    0.41
    POSITIVE LOGITS
    INITIAL
    0.52
    programa
    0.50
    ன்த
    0.50
    initial
    0.49
    such
    0.46
    inol
    0.44
    chosen
    0.44
    erei
    0.44
    oxet
    0.44
    rna
    0.43
    Activations Density 0.000%

    No Known Activations