© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65247
    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_46_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
     бү
    0.41
    Qw
    0.41
     Jav
    0.40
    रुण
    0.39
     Java
    0.39
     Holland
    0.38
    ндан
    0.38
    (`./
    0.37
     जावा
    0.37
    Java
    0.37
    POSITIVE LOGITS
    racted
    0.38
     ছিলাম
    0.37
     იყო
    0.37
     গ্রন্থ
    0.36
    वाया
    0.36
     obligatorio
    0.36
     Particip
    0.36
    ísimo
    0.36
     बोलो
    0.36
    rias
    0.35
    Activations Density 0.000%

    No Known Activations