© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258573
    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_22_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
     daño
    0.46
     amante
    0.45
     savent
    0.45
    眎
    0.45
     ಆದರೆ
    0.44
    網友
    0.44
     परफेक्ट
    0.44
     выбо
    0.43
     باستخدام
    0.42
    诩
    0.42
    POSITIVE LOGITS
    vency
    0.44
     व्हेल
    0.41
    esters
    0.40
    mus
    0.39
     #${
    0.39
    ከናወ
    0.38
    CDS
    0.37
     ECB
    0.37
    cence
    0.37
     శు
    0.37
    Activations Density 0.000%

    No Known Activations