© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33213
    Prev
    Next
    INDEX
    Explanations

    get element by id

    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_7_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
    (
    1.26
    ي
    1.24
    I
    1.07
    ו
    1.05
    P
    1.05
    B
    1.01
    ();
    0.97
    C
    0.91
    ('
    0.88
    يد
    0.87
    POSITIVE LOGITS
    d
    0.88
     Thrive
    0.87
    lng
    0.78
    g
    0.77
    zied
    0.76
     Reels
    0.75
     other
    0.75
    c
    0.74
    ,
    0.74
     Focusing
    0.73
    Activations Density 0.001%

    No Known Activations