© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62256
    Prev
    Next
    INDEX
    Explanations

    common code sounds

    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_59_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
    โ
    1.39
     ro
    0.89
    ro
    0.86
    fo
    0.84
     Ro
    0.79
     Fo
    0.74
    Ro
    0.74
     xo
    0.74
     رو
    0.73
    ﾎ
    0.73
    POSITIVE LOGITS
     नारा
    0.34
     dumpfile
    0.33
     palate
    0.33
     instrumentality
    0.33
    RIBE
    0.32
     cited
    0.31
    িতায়
    0.31
    TabLayout
    0.31
     পত্রিকার
    0.31
    ufieurs
    0.31
    Activations Density 0.019%

    No Known Activations