© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149097
    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_23_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
    njih
    0.54
     ප්‍රති
    0.47
    Earth
    0.47
     телефона
    0.46
    ܨ
    0.46
    pren
    0.46
    École
    0.45
    ﻃ
    0.45
    రుగులు
    0.45
    ﺽ
    0.44
    POSITIVE LOGITS
     curvatures
    0.52
    保证金
    0.49
     mus
    0.48
     amortization
    0.46
     resets
    0.45
     motiv
    0.44
     erasure
    0.44
     worsening
    0.44
     Instrumentation
    0.43
     বজায়
    0.42
    Activations Density 0.000%

    No Known Activations