© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    nia
    0.68
    rd
    0.67
    nh
    0.66
    niak
    0.63
    r
    0.60
    ns
    0.60
    nan
    0.59
    nv
    0.59
    gr
    0.57
    ra
    0.57
    POSITIVE LOGITS
    ψ
    0.59
    με
    0.51
    α
    0.50
    <0xE0>
    0.47
    ό
    0.46
    ✕
    0.46
    лі
    0.45
    ме
    0.45
    έ
    0.45
    مت
    0.44
    Activations Density 0.000%

    No Known Activations