© 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. 204514
    Prev
    Next
    INDEX
    Explanations

    import pandas for python

    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
     cốt
    0.39
     tokenId
    0.38
     foul
    0.37
    助
    0.36
    oul
    0.36
    }(-
    0.35
     fazla
    0.35
     يص
    0.35
    鐩
    0.34
     அறிய
    0.34
    POSITIVE LOGITS
     importation
    0.47
    구를
    0.43
    orescence
    0.42
    ctuations
    0.41
    시고
    0.41
    RPM
    0.41
     Zam
    0.40
    javab
    0.39
    RGB
    0.38
    contra
    0.37
    Activations Density 0.001%

    No Known Activations