© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42382
    Prev
    Next
    INDEX
    Explanations

    CH codes, chemical notations, and specific terms

    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_3_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
     you
    0.86
    n
    0.82
    ０
    0.72
     anál
    0.71
    ۹
    0.70
    0
    0.69
     infidelity
    0.68
     économ
    0.68
     there
    0.67
     vacancies
    0.67
    POSITIVE LOGITS
    U
    0.85
    S
    0.81
    I
    0.81
    AR
    0.80
    Ges
    0.78
    YC
    0.78
    ST
    0.73
    AT
    0.70
    OL
    0.70
    os
    0.69
    Activations Density 0.011%

    No Known Activations