© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63848
    Prev
    Next
    INDEX
    Explanations

    query search

    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_46_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
    pile
    0.40
    ើង
    0.37
     Seung
    0.36
     Duck
    0.36
     काट
    0.36
    蓮
    0.35
    PROVIDED
    0.35
     النار
    0.35
    혐
    0.35
    Duck
    0.34
    POSITIVE LOGITS
    สำหรับการ
    0.37
     καλ
    0.36
    럿
    0.35
    zg
    0.35
     micró
    0.34
    Aslamualaikum
    0.34
     Kob
    0.34
    rej
    0.34
    Timelapse
    0.33
    ஜ்
    0.33
    Activations Density 0.001%

    No Known Activations