© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199397
    Prev
    Next
    INDEX
    Explanations

    It

    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
    𝚅
    0.44
    ച
    0.43
     VOLUME
    0.39
     كانت
    0.38
    લી
    0.38
    ampak
    0.36
    াইব
    0.36
    appeal
    0.36
    ੰ
    0.36
     تمہ
    0.35
    POSITIVE LOGITS
     மீட்ப
    0.43
     絶対
    0.42
    گرم
    0.40
     vrát
    0.38
    warp
    0.38
     рода
    0.37
     flash
    0.37
     tent
    0.36
    emás
    0.36
    Scheduler
    0.36
    Activations Density 0.003%

    No Known Activations