© 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. 87139
    Prev
    Next
    INDEX
    Explanations

    clapioudouchy

    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
    ൬
    0.63
     современ
    0.62
     уве
    0.60
    horizontalLayout
    0.60
    ເລັກ
    0.59
    声道
    0.59
    ፩
    0.59
     ако
    0.58
    h
    0.57
    ສ່ວນ
    0.57
    POSITIVE LOGITS
    0.96
    ens
    0.76
    ST
    0.74
    ang
    0.73
    ess
    0.73
    та
    0.71
    EN
    0.71
    ol
    0.71
    im
    0.70
    IAM
    0.68
    Activations Density 0.000%

    No Known Activations