© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98115
    Prev
    Next
    INDEX
    Explanations

    IP address ranges or CIDR

    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_14_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
     stati
    0.40
     m
    0.34
     separations
    0.32
     kaps
    0.32
     partis
    0.32
     tahan
    0.31
     behandling
    0.31
     biri
    0.30
     sulfur
    0.30
     har
    0.30
    POSITIVE LOGITS
    ى
    0.39
    as
    0.37
    ע
    0.33
    Play
    0.33
    o
    0.33
    et
    0.32
    <0x0D>
    0.32
    City
    0.32
    у
    0.31
    ع
    0.31
    Activations Density 0.006%

    No Known Activations