© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144060
    Prev
    Next
    INDEX
    Explanations

    legal liability conditions

    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_0_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
    tı
    1.90
    нг
    1.77
    та
    1.73
    з
    1.67
    ى
    1.67
    т
    1.65
    не
    1.60
    ется
    1.59
    ции
    1.53
    ння
    1.53
    POSITIVE LOGITS
    '
    2.52
    R
    2.36
    H
    2.25
    N
    2.19
    S
    2.17
    T
    2.14
    G
    2.09
    P
    2.08
    B
    2.05
    F
    2.05
    Activations Density 0.001%

    No Known Activations