© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44891
    Prev
    Next
    INDEX
    Explanations

    names of people, often preceded by Ryan

    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
    ب
    0.70
    }
    0.66
    :
    0.63
    는
    0.62
    )"))
    0.59
    يا
    0.57
    "}
    0.56
    Was
    0.55
    Zespół
    0.54
    was
    0.53
    POSITIVE LOGITS
    z
    0.74
    ار
    0.73
    р
    0.72
    m
    0.71
    v
    0.68
    ן
    0.67
    ри
    0.66
    in
    0.66
    ur
    0.64
    il
    0.63
    Activations Density 0.000%

    No Known Activations