© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241975
    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_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     बीन
    0.40
    ttamente
    0.37
     Taw
    0.37
     attest
    0.36
     Porque
    0.36
     coda
    0.36
     Gaud
    0.35
    드로
    0.34
     MESS
    0.34
    値
    0.34
    POSITIVE LOGITS
    imagine
    0.43
    ългария
    0.42
    inite
    0.40
     excluding
    0.38
     डीएल
    0.38
    bergh
    0.38
    igues
    0.38
    குடும்ப
    0.38
     }()
    0.38
    coons
    0.37
    Activations Density 0.000%

    No Known Activations