© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161288
    Prev
    Next
    INDEX
    Explanations

    Hebrew, Arabic, or similar greetings/phrases

    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_2_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
    ור
    1.67
     It
    1.34
     can
    1.29
    은
    1.23
    ма
    1.17
    ות
    1.13
     Haziran
    1.13
    고
    1.09
    ла
    1.09
    카페
    1.05
    POSITIVE LOGITS
    um
    1.31
    s
    1.15
    ra
    1.10
    ments
    1.08
    ن
    1.08
    am
    1.03
    8
    1.03
    in
    1.02
    ryk
    0.97
    od
    0.96
    Activations Density 0.001%

    No Known Activations