© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218147
    Prev
    Next
    INDEX
    Explanations

    coffee mug

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    <sup>
    0.42
    shelf
    0.36
    ค้า
    0.36
    anamh
    0.36
    unakan
    0.35
    gimento
    0.35
    の値
    0.35
    dual
    0.34
    杵
    0.34
    مت
    0.34
    POSITIVE LOGITS
     लो
    0.44
     CCM
    0.43
    omé
    0.43
     quilted
    0.43
     indes
    0.43
     XMFLOAT
    0.42
     Mueller
    0.42
     Lorenzo
    0.41
     Gomez
    0.41
    QUIN
    0.41
    Activations Density 0.002%

    No Known Activations