© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14898
    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_13_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
    ويس
    0.55
    सल
    0.53
    če
    0.53
     sadrž
    0.53
    ς
    0.52
    <0x85>
    0.51
    ли
    0.50
    れます
    0.49
    ó
    0.47
    л
    0.47
    POSITIVE LOGITS
     wander
    0.52
    in
    0.50
    IN
    0.47
     mischiev
    0.47
    aadhar
    0.47
     wandering
    0.46
     wanders
    0.44
    成り
    0.44
    囲
    0.44
    ampton
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.