© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110567
    Prev
    Next
    INDEX
    Explanations

    universally followed by descriptive words

    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
    د
    1.61
    َ
    1.55
    то
    1.52
    ات
    1.41
    ية
    1.33
    ли
    1.27
    יות
    1.18
    ർ
    1.14
    ان
    1.12
    д
    1.11
    POSITIVE LOGITS
    com
    1.23
    are
    1.13
     are
    1.10
     as
    1.08
    ol
    0.97
    وک
    0.96
     a
    0.95
    oo
    0.95
    amak
    0.95
    hna
    0.92
    Activations Density 0.001%

    No Known Activations