© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14065
    Prev
    Next
    INDEX
    Explanations

    hexadecimal sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_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
    TIME
    0.41
    m
    0.38
    N
    0.37
     சூர
    0.35
    NO
    0.35
    Param
    0.34
    AME
    0.34
    KOM
    0.34
    LINE
    0.34
    PROCESS
    0.34
    POSITIVE LOGITS
     impasse
    0.38
     staircase
    0.35
    <0x0D>
    0.35
     spiral
    0.35
     billiard
    0.35
    閔
    0.33
    鵠
    0.33
     Adirond
    0.32
     thinking
    0.32
     dunk
    0.32
    Activations Density 0.024%

    No Known Activations