© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236768
    Prev
    Next
    INDEX
    Explanations

    precede firstline by putting Sure

    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_25_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
    θο
    0.17
    ந்தோ
    0.16
    ústria
    0.16
     文字
    0.16
    
    0.15
    ിവ
    0.15
    entionally
    0.14
    蚜
    0.14
     comunidades
    0.14
     الجيش
    0.14
    POSITIVE LOGITS
     Lakshmi
    0.15
     pięk
    0.14
     solubilities
    0.14
    चिक
    0.14
     იქნება
    0.14
     갔
    0.14
    hFile
    0.14
    utsche
    0.14
     aspirants
    0.14
     recommande
    0.14
    Activations Density 0.000%

    No Known Activations