© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85086
    Prev
    Next
    INDEX
    Explanations

    email disappearing

    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_23_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
     ears
    0.42
     deafness
    0.41
     taller
    0.39
     accurate
    0.39
     debts
    0.38
     next
    0.38
    ນ
    0.38
     bells
    0.38
     Bears
    0.38
     debt
    0.37
    POSITIVE LOGITS
    pertino
    0.38
     Сьогодні
    0.37
    ப்பதற்கு
    0.36
     sejahtera
    0.36
    表明
    0.36
    岫
    0.36
    ද්ග
    0.35
    rante
    0.34
    στηκε
    0.34
     Fiscal
    0.34
    Activations Density 0.000%

    No Known Activations