© 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. 108616
    Prev
    Next
    INDEX
    Explanations

    flair

    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
    ت
    1.58
    ب
    1.23
    ق
    1.16
    को
    1.16
    كان
    1.15
    تين
    1.10
    ას
    1.08
    تك
    1.08
    },
    1.05
    الية
    1.05
    POSITIVE LOGITS
    า
    1.56
    ى
    1.30
    ำ
    1.26
    ری
    1.13
    ry
    1.12
    й
    1.05
    ным
    1.02
    ो
    1.02
    ้า
    0.99
    al
    0.96
    Activations Density 0.000%

    No Known Activations