© 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. 20512
    Prev
    Next
    INDEX
    Explanations

    wildcard symbols

    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
    [
    0.45
    Ministry
    0.42
    $-$,
    0.38
    "(
    0.37
    ---
    0.36
    ১১
    0.36
    _=
    0.35
    Disc
    0.35
    Survival
    0.35
    "+
    0.34
    POSITIVE LOGITS
     import
    0.66
     importation
    0.63
     export
    0.59
     Importing
    0.58
     importing
    0.57
     exportation
    0.57
     exports
    0.56
     imports
    0.56
     आयात
    0.55
     Import
    0.55
    Activations Density 0.000%

    No Known Activations