© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111691
    Prev
    Next
    INDEX
    Explanations

    común / comúns

    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_2_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
    in
    1.66
    ن
    1.37
    ם
    1.31
    不
    1.27
    ا
    1.27
    มี
    1.23
    中心
    1.20
    你
    1.20
    𝟮
    1.18
    ב
    1.14
    POSITIVE LOGITS
    dır
    1.37
    ли
    1.24
    스
    1.15
    <0x80>
    0.95
    g
    0.95
     descendant
    0.93
    κο
    0.91
    idé
    0.89
     disorganized
    0.89
    ುದ
    0.89
    Activations Density 0.001%

    No Known Activations