© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111801
    Prev
    Next
    INDEX
    Explanations

    casi ,casí ,casí

    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
    의
    1.57
    is
    1.42
    ка
    1.40
    아
    1.34
    지
    1.29
    га
    1.26
    ки
    1.23
    の
    1.19
    it
    1.12
    ق
    1.11
    POSITIVE LOGITS
    -
    1.48
    IES
    0.97
    ль
    0.94
     $>$
    0.91
    ined
    0.88
     zacz
    0.85
    /
    0.85
    CR
    0.84
     rozpoczę
    0.84
    สิ่ง
    0.83
    Activations Density 0.006%

    No Known Activations