© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206836
    Prev
    Next
    INDEX
    Explanations

    and then

    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_19_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
    ik
    0.45
    wa
    0.38
    stieg
    0.37
    نی
    0.37
     نی
    0.36
     사회
    0.36
     {'
    0.36
    ว
    0.36
    ély
    0.35
    iky
    0.35
    POSITIVE LOGITS
    عية
    0.40
    渉
    0.40
    ದ್ಧ
    0.36
     WHETHER
    0.36
    বারের
    0.35
     маркетин
    0.33
     Expenditures
    0.33
     adesso
    0.33
     agosto
    0.33
     PRES
    0.33
    Activations Density 0.025%

    No Known Activations