© 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. 123234
    Prev
    Next
    INDEX
    Explanations

    cumin

    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
    .
    0.68
    T
    0.62
    /
    0.58
    也
    0.57
    ur
    0.57
    LAS
    0.55
    L
    0.53
    LF
    0.52
    不一樣
    0.52
    '
    0.52
    POSITIVE LOGITS
    ки
    0.71
    </strong>
    0.68
     avaient
    0.67
     annuel
    0.67
    ير
    0.66
    ק
    0.66
     tratamiento
    0.66
     طويل
    0.66
     المللی
    0.65
    ق
    0.64
    Activations Density 0.000%

    No Known Activations