© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250487
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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_56_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
     devoted
    0.39
    READ
    0.34
    unique
    0.34
    beet
    0.33
     relativement
    0.33
    பா
    0.32
    แล
    0.32
     '
    0.32
    equals
    0.32
     ഉപ
    0.32
    POSITIVE LOGITS
     VStack
    0.39
     ϕ
    0.38
     ν
    0.37
     minY
    0.37
     #+#
    0.37
     Multis
    0.37
     Turnier
    0.36
     nonconvex
    0.36
     Motorsport
    0.36
    ′,
    0.36
    Activations Density 0.002%

    No Known Activations