© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129826
    Prev
    Next
    INDEX
    Explanations

    Japanese words and characters

    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_1_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
    \
    1.74
    ي
    1.41
    ون
    1.25
     is
    1.21
    }$.
    1.18
    د
    1.10
     with
    1.01
    ен
    0.96
    ان
    0.93
    </u>
    0.93
    POSITIVE LOGITS
     recib
    1.16
    hwa
    1.07
     recibieron
    1.03
     pusieron
    1.02
    他
    1.02
     anunci
    1.02
     hicieron
    1.01
    tiene
    0.98
    قیع
    0.96
    hlt
    0.95
    Activations Density 0.000%

    No Known Activations