© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199353
    Prev
    Next
    INDEX
    Explanations

    academic research papers

    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_50_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
    솥
    0.46
    ᄃ
    0.46
    लेट
    0.42
     Yves
    0.40
     Catalan
    0.39
     Barbie
    0.38
     Yara
    0.38
     Cole
    0.38
     ইয়
    0.38
    ியல்
    0.38
    POSITIVE LOGITS
    屯
    0.44
    オブ
    0.44
    HW
    0.42
    明日
    0.41
    hto
    0.39
    جوم
    0.39
    荕
    0.38
    Jer
    0.38
    津
    0.37
    ੩
    0.37
    Activations Density 0.000%

    No Known Activations