© 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. 143196
    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
     "="
    0.59
     Kherson
    0.56
     commensurate
    0.56
     compressor
    0.55
     SDP
    0.55
     versatility
    0.55
     Rupees
    0.55
     paragon
    0.54
     generosity
    0.53
     Almighty
    0.53
    POSITIVE LOGITS
     و
    0.55
    US
    0.53
    watching
    0.53
    Retro
    0.53
    FE
    0.52
    C
    0.52
    CI
    0.51
    Birds
    0.51
    Core
    0.50
    关于
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.