© 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. 93445
    Prev
    Next
    INDEX
    Explanations

    trends and changes

    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
     enseñanzas
    0.63
    clickView
    0.60
    ем
    0.59
    extrémité
    0.59
    empê
    0.58
     Antennes
    0.57
     extrémités
    0.57
    키
    0.57
     hoà
    0.57
    bindingFields
    0.57
    POSITIVE LOGITS
    s
    0.83
    J
    0.71
    <h2>
    0.64
    z
    0.61
    A
    0.60
    N
    0.60
     j
    0.57
     sugar
    0.57
     bonus
    0.55
     Bonus
    0.55
    Activations Density 0.005%

    No Known Activations