© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108917
    Prev
    Next
    INDEX
    Explanations

    arabic or waifu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    ين
    1.66
     to
    1.58
     be
    1.43
    يد
    1.30
     can
    1.22
    ור
    1.22
    б
    1.20
     have
    1.10
    та
    1.09
     has
    1.09
    POSITIVE LOGITS
    కు
    1.03
    am
    0.98
    ために
    0.95
    𝘢
    0.90
    us
    0.88
    ت
    0.86
    ির
    0.83
    पणे
    0.83
    oric
    0.80
    지
    0.79
    Activations Density 0.000%

    No Known Activations