© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8950
    Prev
    Next
    INDEX
    Explanations

    ISBN identifiers

    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_13_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
    ج
    0.40
    د
    0.34
    ংশ
    0.34
    NSY
    0.32
    itism
    0.31
    ifs
    0.31
    大規模
    0.31
     நிவார
    0.31
     EXECUTIVE
    0.31
     ਪ
    0.30
    POSITIVE LOGITS
     него
    0.41
     mengingat
    0.40
     ISBN
    0.40
     njega
    0.38
    ISBN
    0.38
     '?
    0.37
    <0xF1>
    0.35
    тери
    0.35
     sete
    0.35
    이나
    0.35
    Activations Density 0.017%

    No Known Activations