© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3020
    Prev
    Next
    INDEX
    Explanations

    gospel music and pies

    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
    oč
    0.37
     Kami
    0.36
     phận
    0.36
     ख
    0.36
     Pip
    0.35
     pip
    0.35
     Cous
    0.35
    ឯ
    0.35
    ৌজ
    0.35
    解除
    0.35
    POSITIVE LOGITS
     gospel
    0.58
    cabin
    0.49
     Gospel
    0.47
     camp
    0.47
     hymn
    0.46
     quart
    0.45
     Quart
    0.44
    camp
    0.44
     hym
    0.44
     quartet
    0.43
    Activations Density 0.028%

    No Known Activations