© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219936
    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_31_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
     noble
    0.33
    ĕ
    0.33
     etiquette
    0.33
    ίν
    0.32
     exponents
    0.32
    乂
    0.31
    ۆر
    0.31
    <0xE1>
    0.31
     exponent
    0.31
    等
    0.31
    POSITIVE LOGITS
    Buyers
    0.39
     பொறிய
    0.38
     tenetur
    0.37
     campuses
    0.36
     여러분
    0.35
    キャラ
    0.35
     EVIDENCE
    0.35
     Ambiental
    0.34
     fichier
    0.34
     Datei
    0.34
    Activations Density 0.000%

    No Known Activations