© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58932
    Prev
    Next
    INDEX
    Explanations

    approx

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     开发
    0.45
     П
    0.43
     ail
    0.41
     P
    0.40
     ~
    0.39
     CSP
    0.39
     లు
    0.39
     _
    0.38
     NIH
    0.38
     "
    0.38
    POSITIVE LOGITS
    5
    0.76
    6
    0.75
    3
    0.73
    8
    0.73
    9
    0.69
    About
    0.68
    7
    0.63
    1
    0.61
    4
    0.60
    2
    0.59
    Activations Density 0.001%

    No Known Activations