© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228922
    Prev
    Next
    INDEX
    Explanations

    function definitions and code blocks

    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_6_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
    اً
    1.14
    ی
    1.03
    ه
    0.95
    راہیم
    0.93
    ร
    0.93
    Acetoxy
    0.92
    ᓘ
    0.92
    Ꮭ
    0.91
    라
    0.90
    고
    0.85
    POSITIVE LOGITS
    um
    1.41
    em
    1.25
    ok
    1.21
    ay
    1.10
    ü
    1.10
    ak
    1.09
    f
    1.09
    ist
    1.08
    inen
    1.05
    \
    1.04
    Activations Density 0.000%

    No Known Activations