© 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. 138572
    Prev
    Next
    INDEX
    Explanations

    anchor href

    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
     Readiness
    0.41
     piernas
    0.39
    ghum
    0.38
    ropolis
    0.37
    detector
    0.36
    ↥
    0.36
     भूमिका
    0.36
    jpeg
    0.36
     visage
    0.35
    physiology
    0.35
    POSITIVE LOGITS
     Ether
    0.43
    alama
    0.42
     reinstall
    0.37
     '$(
    0.37
    拍卖
    0.37
     PROBLE
    0.36
     आंच
    0.36
    ಪ್ರ
    0.36
    ixon
    0.35
     Main
    0.35
    Activations Density 0.001%

    No Known Activations