© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147373
    Prev
    Next
    INDEX
    Explanations

    RO

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    I
    0.71
    IAT
    0.52
    าล
    0.48
    MUL
    0.40
    NAME
    0.40
    POM
    0.40
    ی
    0.40
    NATO
    0.39
    IOT
    0.39
    M
    0.39
    POSITIVE LOGITS
    ck
    0.49
    lle
    0.48
    lation
    0.46
    cky
    0.46
    sc
    0.45
    lia
    0.45
    theless
    0.45
    tudo
    0.44
    lla
    0.44
    st
    0.43
    Activations Density 0.000%

    No Known Activations