© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142870
    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_0_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
    و
    0.93
    ו
    0.81
    お
    0.74
    ش
    0.70
    ع
    0.66
    ো
    0.64
    ш
    0.62
    ש
    0.60
    الح
    0.57
    ח
    0.57
    POSITIVE LOGITS
    )
    0.63
     accountNumber
    0.59
     लेनदेन
    0.59
    JlcG
    0.57
    chainId
    0.56
    btnClose
    0.56
    Predicate
    0.55
     shouldUse
    0.54
    ainak
    0.54
    umeric
    0.53
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.