© 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. 122578
    Prev
    Next
    INDEX
    Explanations

    evocative

    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
     withered
    0.71
    нат
    0.70
     metà
    0.70
     distância
    0.68
    ถาน
    0.68
     headcount
    0.68
    ק
    0.68
    ун
    0.67
     sawdust
    0.67
    ดิน
    0.66
    POSITIVE LOGITS
    ED
    0.94
    It
    0.93
    AY
    0.80
    ERS
    0.78
    Aug
    0.73
    A
    0.73
    :
    0.73
    IC
    0.71
    sl
    0.71
    ors
    0.71
    Activations Density 0.000%

    No Known Activations