© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41706
    Prev
    Next
    INDEX
    Explanations

    bass drum boost response

    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_3_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
     culto
    0.63
     blood
    0.59
     guitar
    0.59
    れ
    0.59
    ಲ
    0.59
    िल
    0.59
     coffee
    0.59
    पणे
    0.58
    れる
    0.57
     browser
    0.56
    POSITIVE LOGITS
    c
    0.67
    ",
    0.63
    ه
    0.63
    },
    0.63
    bry
    0.59
    for
    0.59
    <
    0.59
    cms
    0.58
    liga
    0.58
    cinn
    0.57
    Activations Density 0.003%

    No Known Activations