© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86802
    Prev
    Next
    INDEX
    Explanations

    plugin extensions

    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_18_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
     亠
    0.42
    ิน
    0.41
    细菌
    0.41
    ும்
    0.41
     이미지
    0.41
    UserSettings
    0.41
    <0x99>
    0.41
    نج
    0.40
     angiogenesis
    0.40
     waterproofing
    0.40
    POSITIVE LOGITS
     Veloc
    0.46
    to
    0.44
    ючись
    0.44
    Give
    0.41
    Boards
    0.41
    through
    0.41
    swith
    0.41
    给自己
    0.41
    Plus
    0.40
    ®,
    0.40
    Activations Density 0.002%

    No Known Activations