© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59179
    Prev
    Next
    INDEX
    Explanations

    database names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Es
    0.46
    est
    0.44
    ेष
    0.43
    u
    0.40
    es
    0.40
    PO
    0.38
    ate
    0.38
     ods
    0.38
    ​]]
    0.38
    art
    0.37
    POSITIVE LOGITS
     demo
    0.68
     Demo
    0.64
     demos
    0.63
    Demo
    0.61
    demo
    0.54
    demos
    0.46
    ISION
    0.43
    obbies
    0.43
    akati
    0.41
     Dat
    0.40
    Activations Density 0.000%

    No Known Activations