© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 56781
    Prev
    Next
    INDEX
    Explanations

    "already", "if", "not yet"

    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
     to
    0.74
    in
    0.62
    कहां
    0.61
    Tempo
    0.59
    에서는
    0.59
    6
    0.58
    </h2>
    0.57
     stopni
    0.57
    ých
    0.56
    回り
    0.56
    POSITIVE LOGITS
    '};
    0.60
    स्परिक
    0.54
    داد
    0.54
     IncludeField
    0.53
    ıda
    0.52
     مُ
    0.52
    BLACKLIST
    0.51
     sufrimiento
    0.51
    URNIZOR
    0.50
    UserId
    0.50
    Activations Density 0.000%

    No Known Activations