© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91497
    Prev
    Next
    INDEX
    Explanations

    learning approaches and classifier

    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_3_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
    та
    0.78
     trabajo
    0.75
    ؟
    0.71
     установлено
    0.70
    ти
    0.68
    ti
    0.67
     состояние
    0.67
     torture
    0.67
     juicio
    0.67
     sanciones
    0.67
    POSITIVE LOGITS
    B
    0.80
    m
    0.73
    T
    0.73
    V
    0.71
    A
    0.70
    S
    0.68
    M
    0.67
    L
    0.67
    G
    0.66
    o
    0.66
    Activations Density 0.003%

    No Known Activations