© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50092
    Prev
    Next
    INDEX
    Explanations

    app

    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_30_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
    潾
    0.25
    nom
    0.24
    neos
    0.24
    高峰
    0.24
    unity
    0.24
    ნენ
    0.23
    funeral
    0.23
    堡
    0.23
    শিব
    0.23
    quick
    0.22
    POSITIVE LOGITS
     Smoking
    0.26
     Specific
    0.23
     Situation
    0.22
     specific
    0.22
     CYCLE
    0.21
     NULL
    0.21
     transactions
    0.20
     smoking
    0.20
     Wehr
    0.20
     Rug
    0.20
    Activations Density 0.002%

    No Known Activations