© 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. 61671
    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
     tripled
    0.44
    ندق
    0.41
     lui
    0.40
     njima
    0.40
     axially
    0.38
    <0xB9>
    0.38
    ８
    0.37
    茍
    0.37
     terakhir
    0.37
    彼の
    0.37
    POSITIVE LOGITS
     as
    0.50
     wrote
    0.49
    wrote
    0.49
    Top
    0.46
    を行った
    0.42
    HERS
    0.41
     პირადი
    0.41
     escribió
    0.41
    NO
    0.41
    なった
    0.40
    Activations Density 0.000%

    No Known Activations