© 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. 130074
    Prev
    Next
    INDEX
    Explanations

    dyeing or dyed substances

    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
    ่
    1.04
    ία
    1.01
     I
    0.99
    operatorname
    0.96
    ство
    0.91
    ת
    0.91
    ן
    0.90
    getInstance
    0.89
     to
    0.88
    ר
    0.87
    POSITIVE LOGITS
    _
    1.78
    \
    1.28
    en
    1.21
    س
    1.17
    ong
    1.16
     pathogens
    1.09
    ções
    1.02
    них
    1.02
    -
    1.02
    t
    1.02
    Activations Density 0.000%

    No Known Activations