© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10074
    Prev
    Next
    INDEX
    Explanations

    to the

    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_13_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
    `}
    0.59
    货物
    0.58
     onderwerp
    0.57
     Incluso
    0.57
     Veamos
    0.54
     Quais
    0.54
    直到
    0.54
     Girona
    0.53
     Quiero
    0.52
     Confira
    0.52
    POSITIVE LOGITS
     managerial
    0.57
    ilir
    0.55
    aría
    0.50
     monet
    0.48
    aved
    0.47
    😐
    0.47
    at
    0.47
    archie
    0.47
    inded
    0.46
    तील
    0.46
    Activations Density 0.018%

    No Known Activations