© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50540
    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_30_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
     discharge
    0.50
    ur
    0.48
    aw
    0.48
    ᱪ
    0.48
    ad
    0.46
    า
    0.46
    ing
    0.46
    ill
    0.46
    ا
    0.46
    ات
    0.45
    POSITIVE LOGITS
     Verstappen
    0.55
     USDT
    0.55
     EET
    0.53
     PlayerSelector
    0.53
    lEdit
    0.52
     ഗവേഷ
    0.52
     VEGFR
    0.52
     Vettel
    0.51
    lež
    0.51
     PoE
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.