© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87840
    Prev
    Next
    INDEX
    Explanations

    math functions

    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_60_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
     greater
    0.39
     Mov
    0.37
     number
    0.37
     définie
    0.36
     spring
    0.36
     mov
    0.36
    0.35
     finale
    0.35
     c
    0.35
     Compliance
    0.35
    POSITIVE LOGITS
    min
    0.58
    because
    0.50
    sup
    0.50
    inf
    0.47
    tanh
    0.47
     because
    0.46
    log
    0.46
    max
    0.45
    sin
    0.44
    lim
    0.44
    Activations Density 0.000%

    No Known Activations