© 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. 61442
    Prev
    Next
    INDEX
    Explanations

    easel, stand, pad, sketchbook

    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
     wrestler
    0.58
    you
    0.56
     interrogate
    0.53
     información
    0.52
    ４
    0.52
     informacion
    0.52
    ſs
    0.52
    ბ
    0.51
    情報の
    0.50
    ５
    0.50
    POSITIVE LOGITS
     الكثير
    0.57
     ла
    0.56
     серии
    0.55
     ولم
    0.55
     بدون
    0.54
     इंद
    0.54
    ottle
    0.53
     अवेलेबल
    0.53
    lerine
    0.52
     местности
    0.52
    Activations Density 0.000%

    No Known Activations