© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205288
    Prev
    Next
    INDEX
    Explanations

    derivative with respect to

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     leadership
    0.37
    ="${
    0.36
     Team
    0.36
     fig
    0.36
    zyn
    0.35
    DataSet
    0.35
     DataSet
    0.35
     қили
    0.35
     위
    0.35
    phyr
    0.34
    POSITIVE LOGITS
    ucionales
    0.39
     হেঁটে
    0.38
     нуля
    0.37
     outs
    0.37
    ུ་
    0.37
     중요하다
    0.37
    ნიშვნელ
    0.36
    च्चय
    0.35
    lonitrile
    0.35
     जहां
    0.35
    Activations Density 0.002%

    No Known Activations