© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107392
    Prev
    Next
    INDEX
    Explanations

    contralateral, contrails, chemtrails

    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_2_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
    ↵
    1.19
    ید
    1.14
     de
    0.95
     have
    0.95
    د
    0.93
    Have
    0.91
     couronne
    0.90
    P
    0.89
    ก็
    0.88
    ദ്യം
    0.88
    POSITIVE LOGITS
    та
    1.20
    :
    1.04
    <0x80>
    0.99
    rl
    0.98
    ை
    0.97
    ronics
    0.96
    iz
    0.95
    rs
    0.95
    ul
    0.93
    t
    0.93
    Activations Density 0.003%

    No Known Activations