© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195508
    Prev
    Next
    INDEX
    Explanations

    the ice cream 淇淋

    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_15_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
    s
    0.63
    n
    0.55
     South
    0.53
    mt
    0.49
    d
    0.47
     solace
    0.47
    asting
    0.47
     Type
    0.47
     Ac
    0.46
    ?:
    0.46
    POSITIVE LOGITS
     עד
    0.50
     역할
    0.49
     봐
    0.48
    עד
    0.47
     громад
    0.47
     বস্ত্র
    0.47
     법칙
    0.46
     것이
    0.46
     기간
    0.46
     الوق
    0.46
    Activations Density 0.000%

    No Known Activations