© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153395
    Prev
    Next
    INDEX
    Explanations

    extracting text from html

    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_23_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
     tzv
    0.17
    ายเป็น
    0.17
     nicknamed
    0.16
    ipid
    0.16
    バトル
    0.15
     آقای
    0.15
    闥
    0.15
    هداف
    0.15
     shaved
    0.15
     Atlet
    0.15
    POSITIVE LOGITS
    tracing
    0.16
    userDetail
    0.15
    oding
    0.15
     후
    0.14
     wzglę
    0.14
    Verification
    0.14
     checklists
    0.14
     Acc
    0.14
     tý
    0.14
     자세
    0.14
    Activations Density 0.000%

    No Known Activations