© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212333
    Prev
    Next
    INDEX
    Explanations

    Czech and related sequences

    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_5_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
    A
    1.32
    ור
    1.23
     agreg
    1.12
    ;
    1.11
     destac
    1.07
    n
    1.05
    )。
    1.05
    밂
    1.02
     przyję
    1.00
    됐
    1.00
    POSITIVE LOGITS
    و
    1.19
    iz
    1.16
    ø
    1.09
    ی
    1.05
    א
    1.03
    িন
    0.98
    я
    0.98
    ᱤ
    0.96
    ы
    0.95
    ING
    0.94
    Activations Density 0.000%

    No Known Activations