© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24544
    Prev
    Next
    INDEX
    Explanations

    add-ons and extensions

    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_10_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
    ,
    0.46
     Donor
    0.43
    ą
    0.42
    ين
    0.41
    .。
    0.40
     Bedarf
    0.40
     بسرعة
    0.40
    ီ
    0.39
     子
    0.39
    ॉन
    0.39
    POSITIVE LOGITS
    ן
    0.62
    a
    0.60
    ~\
    0.53
    one
    0.51
    addons
    0.51
    ﻢ
    0.50
    ा
    0.50
    therefore
    0.48
    รางวัล
    0.48
    </h3>
    0.48
    Activations Density 0.026%

    No Known Activations