© 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. 166618
    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
     analisis
    0.42
    krét
    0.42
    𒌋
    0.41
     uk
    0.39
    Uk
    0.38
     फैक्टर
    0.37
     alé
    0.37
     floribus
    0.36
     análisis
    0.36
     conclude
    0.36
    POSITIVE LOGITS
     NodeJS
    0.35
    assy
    0.35
     BigDecimal
    0.35
     emitting
    0.34
    overflow
    0.34
    walled
    0.33
    แนว
    0.33
    ból
    0.33
    衣
    0.33
     করিয়াছে
    0.32
    Activations Density 0.000%

    No Known Activations