© 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. 123224
    Prev
    Next
    INDEX
    Explanations

    auburn hair

    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
    </h3>
    0.79
    یر
    0.75
    یم
    0.69
    ння
    0.67
    </h4>
    0.66
     sont
    0.65
    یس
    0.62
    </strong>
    0.61
    rients
    0.61
    ک
    0.60
    POSITIVE LOGITS
    t
    1.30
    N
    0.79
    n
    0.79
    <0x80>
    0.75
    V
    0.73
    C
    0.70
    U
    0.69
    ed
    0.69
    R
    0.69
    H
    0.69
    Activations Density 0.000%

    No Known Activations