© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236675
    Prev
    Next
    INDEX
    Explanations

    edges off the bat

    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_25_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
    pm
    0.25
     Arrest
    0.23
    嘗
    0.23
    olog
    0.22
    osis
    0.22
    years
    0.22
    ation
    0.21
    neyland
    0.21
    id
    0.21
     Moses
    0.21
    POSITIVE LOGITS
     méthod
    0.22
     strategie
    0.21
     modific
    0.21
    зму
    0.21
     resistente
    0.21
     zhu
    0.21
     thước
    0.21
    逦
    0.21
    さと
    0.20
     cálculo
    0.20
    Activations Density 0.001%

    No Known Activations