© 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. 34533
    Prev
    Next
    INDEX
    Explanations

    Harriet Tubman and Harper Lee

    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
    of
    0.67
     построе
    0.66
    AC
    0.66
    О
    0.66
    𝗼
    0.65
    दायिक
    0.64
    ۰
    0.63
    ۹
    0.63
    viving
    0.62
     améliorer
    0.61
    POSITIVE LOGITS
    ur
    0.75
    ла
    0.72
    wa
    0.63
    ท
    0.62
     सब्
    0.59
    ↵
    0.59
    تر
    0.59
     Faker
    0.59
    y
    0.58
    w
    0.58
    Activations Density 0.000%

    No Known Activations