© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40182
    Prev
    Next
    INDEX
    Explanations

    Arabic language text

    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_57_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
    ائب
    0.43
    竑
    0.42
    ైన
    0.41
    ائم
    0.41
    ايات
    0.41
    法
    0.41
    妺
    0.41
    統
    0.40
    紘
    0.40
     relied
    0.40
    POSITIVE LOGITS
    za
    0.41
    ch
    0.40
    conf
    0.38
    RB
    0.38
    yr
    0.38
    gb
    0.37
    กระจ
    0.37
    cay
    0.36
    sg
    0.36
    FP
    0.36
    Activations Density 0.000%

    No Known Activations