© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205762
    Prev
    Next
    INDEX
    Explanations

    toddlers

    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_6_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
    i
    1.02
    ö
    1.01
    å
    0.98
    $
    0.95
    oted
    0.89
    "。
    0.86
    ab
    0.82
    al
    0.81
    ä
    0.81
    id
    0.80
    POSITIVE LOGITS
    ের
    1.17
    ж
    1.14
    ים
    1.11
    ों
    1.00
    ς
    0.97
    s
    0.94
    sı
    0.90
    </td>
    0.87
    бр
    0.86
     iterates
    0.85
    Activations Density 0.000%

    No Known Activations