© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35789
    Prev
    Next
    INDEX
    Explanations

    specific names

    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
    f
    0.57
    𝚏
    0.48
    <0x86>
    0.39
    meg
    0.39
    fa
    0.38
    Feels
    0.38
    FA
    0.38
    ｆ
    0.38
    ্লোক
    0.37
    െന്ന
    0.37
    POSITIVE LOGITS
    ாம்
    0.40
     अमल
    0.38
     refrigeration
    0.37
     ').
    0.37
     gilt
    0.37
     ro
    0.36
     perceptions
    0.36
    rosis
    0.36
    ትን
    0.36
    ılıyor
    0.36
    Activations Density 0.002%

    No Known Activations