© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134480
    Prev
    Next
    INDEX
    Explanations

    aml, AML, imal, andan

    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
     كه
    0.96
    ного
    0.91
    ്രീ
    0.89
     تحقيق
    0.88
    ﺭ
    0.86
    rilor
    0.84
    ление
    0.82
    し
    0.82
    ﺰ
    0.82
     Бор
    0.80
    POSITIVE LOGITS
    u
    1.41
    ad
    1.22
    ک
    1.12
    ing
    1.09
    ب
    1.06
    h
    1.05
    f
    1.00
    (
    1.00
    ব
    0.99
    ال
    0.98
    Activations Density 0.000%

    No Known Activations