© 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. 156861
    Prev
    Next
    INDEX
    Explanations

    Arabic letter alef

    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
    و
    1.66
    म
    1.17
    า
    1.16
    на
    1.10
    u
    1.10
    ो
    1.09
    นี่
    1.06
    นั้น
    1.05
    ย
    1.03
    nya
    1.01
    POSITIVE LOGITS
    0
    1.59
     for
    1.41
    ０
    1.16
    ០
    1.12
    ۰
    1.09
    𝟬
    1.05
    ᇂ
    1.01
    ᱹ
    0.99
    ၀
    0.99
    ﺭ
    0.99
    Activations Density 0.000%

    No Known Activations