© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199012
    Prev
    Next
    INDEX
    Explanations

    HTML/JS code snippets

    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_27_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
     lombok
    0.36
    aliśmy
    0.34
    ",
    0.34
     ",
    0.33
     $('
    0.32
    `,
    0.32
     string
    0.31
     chá
    0.31
     franch
    0.31
     Atha
    0.31
    POSITIVE LOGITS
     endometriosis
    0.37
    openjdk
    0.37
     પસંદ
    0.36
     منهج
    0.36
     процес
    0.35
     postup
    0.34
    ೋತಿ
    0.34
    簪
    0.34
    蟋
    0.34
     carries
    0.34
    Activations Density 0.005%

    No Known Activations