© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136201
    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_37_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
    subarray
    0.38
    überkü
    0.36
    Parsed
    0.35
    )|^
    0.35
    Facts
    0.34
    стру
    0.34
    ंख्य
    0.34
     particip
    0.34
     participation
    0.34
     FD
    0.34
    POSITIVE LOGITS
    私が
    0.40
     इंटर
    0.38
    ECTION
    0.37
     blatantly
    0.37
     مساله
    0.36
     nam
    0.35
     originates
    0.35
    ოვნ
    0.35
    翟
    0.35
     Curie
    0.35
    Activations Density 0.000%

    No Known Activations