© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61841
    Prev
    Next
    INDEX
    Explanations

    lose count of time

    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_11_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
     రెడ్డి
    0.56
    ッション
    0.55
    empres
    0.53
    旸
    0.53
    apsing
    0.52
     עס
    0.52
     pensa
    0.52
    ivism
    0.51
     সন্দ
    0.50
     formdata
    0.50
    POSITIVE LOGITS
    ك
    0.89
    C
    0.75
    B
    0.73
    П
    0.73
    ל
    0.71
    ON
    0.70
    Π
    0.69
    На
    0.67
    <0xA5>
    0.66
    ка
    0.64
    Activations Density 0.001%

    No Known Activations