© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21316
    Prev
    Next
    INDEX
    Explanations

    R or 're'

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Rem
    0.57
     remont
    0.56
    REM
    0.45
     Residual
    0.44
     rem
    0.43
    Rem
    0.42
    residual
    0.41
     잔
    0.41
     residual
    0.40
     residuals
    0.40
    POSITIVE LOGITS
     ре
    0.96
     ren
    0.83
    RE
    0.82
     Ре
    0.80
     ré
    0.78
    Ре
    0.75
     ر
    0.71
     Ré
    0.70
     RÉ
    0.70
     র
    0.69
    Activations Density 0.007%

    No Known Activations