© 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. 126658
    Prev
    Next
    INDEX
    Explanations

    adventure rides, five bananas

    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
     وزی
    0.70
    r
    0.69
    Margin
    0.68
    ?")
    0.68
    ۹
    0.66
    л
    0.66
    points
    0.64
    Ι
    0.63
    point
    0.60
     области
    0.60
    POSITIVE LOGITS
    ك
    1.04
    ES
    0.91
    ка
    0.82
    ED
    0.80
    на
    0.77
    ER
    0.77
    ма
    0.73
     jeopard
    0.70
     race
    0.69
     reactor
    0.66
    Activations Density 0.003%

    No Known Activations