© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142799
    Prev
    Next
    INDEX
    Explanations

    short, masculine, singular endings

    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_0_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
    ي
    1.62
    ри
    1.58
    ми
    1.55
    á
    1.49
    리
    1.48
     verrà
    1.36
    し
    1.34
    ции
    1.30
     статью
    1.30
    ет
    1.29
    POSITIVE LOGITS
    of
    1.63
     (
    1.34
    in
    1.29
    p
    1.27
    ikt
    1.20
    er
    1.16
    al
    1.15
    ב
    1.14
    พ
    1.13
    Mad
    1.12
    Activations Density 0.000%

    No Known Activations