© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243602
    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_40_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
    िसिटी
    0.44
    วิธี
    0.42
    眈
    0.41
    Objects
    0.40
     CDs
    0.40
    ὕ
    0.40
    etrically
    0.39
     паци
    0.38
    ಾರ್
    0.37
    Timestamp
    0.37
    POSITIVE LOGITS
     reports
    0.42
     promoted
    0.40
    reports
    0.38
     engineer
    0.38
     promote
    0.37
     Reporting
    0.37
    agena
    0.37
     role
    0.36
     deserving
    0.36
     ඉ
    0.36
    Activations Density 0.000%

    No Known Activations