© 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. 132660
    Prev
    Next
    INDEX
    Explanations

    what

    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
    NOR
    0.41
    اعدة
    0.37
     Inn
    0.36
    obatan
    0.36
     ल
    0.35
    是的
    0.35
    撳
    0.35
    ’
    0.35
    Sach
    0.34
    阂
    0.34
    POSITIVE LOGITS
     paraf
    0.39
    LLO
    0.39
     V
    0.37
     वॉटर
    0.37
    يع
    0.37
    В
    0.37
    texttt
    0.36
    roje
    0.36
     В
    0.35
    く
    0.35
    Activations Density 0.003%

    No Known Activations