© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236250
    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_32_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
    verband
    0.41
     Purchaser
    0.40
     கான்
    0.39
     portant
    0.38
     preventing
    0.38
     empêcher
    0.37
     purchasers
    0.37
    ĝ
    0.37
     purchaser
    0.36
    ņas
    0.36
    POSITIVE LOGITS
     laughs
    0.38
    俵
    0.37
    ̶
    0.37
    豆腐
    0.36
    લિ
    0.36
    தூ
    0.36
    ੳ
    0.36
    䘚
    0.35
    circum
    0.35
     răng
    0.35
    Activations Density 0.000%

    No Known Activations