© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206841
    Prev
    Next
    INDEX
    Explanations

    Replace, use, check, iterate

    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_10_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
    il
    1.16
    ja
    1.13
    ali
    1.05
    ze
    1.04
    ien
    1.02
    í
    1.00
    arrow
    1.00
    ar
    0.99
    lem
    0.97
    isk
    0.97
    POSITIVE LOGITS
    手的
    0.84
    ᱔
    0.76
    制度
    0.73
     použí
    0.71
    ᱐
    0.71
     agré
    0.70
    ум
    0.70
    χή
    0.69
     машиналары
    0.69
     учителя
    0.68
    Activations Density 0.001%

    No Known Activations