© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 60-GEMMASCOPE-2-TRANSCODER-262K
    4. 90661
    Prev
    Next
    INDEX
    Explanations

    say "x"

    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
     Multiply
    0.57
     multiplies
    0.54
    XH
    0.54
     Xer
    0.52
    X
    0.52
     Multiplication
    0.52
     multiply
    0.50
     multiplications
    0.50
    Xr
    0.49
    XO
    0.49
    POSITIVE LOGITS
    in
    0.86
    (
    0.62
     x
    0.60
     m
    0.58
    ?(
    0.55
    u
    0.55
     y
    0.54
    0
    0.53
     g
    0.52
     ?
    0.52
    Activations Density 0.001%

    No Known Activations