© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12200
    Prev
    Next
    INDEX
    Explanations

    ISO standards quality management

    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_40_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
     audits
    0.38
    ниях
    0.38
    inactive
    0.36
     զ
    0.36
    ittings
    0.36
     sunscreen
    0.36
    odesmium
    0.36
     Nigam
    0.35
     cleanest
    0.35
    aniach
    0.35
    POSITIVE LOGITS
     conseil
    0.39
     ново
    0.39
     Consultez
    0.39
    ➣
    0.37
    словно
    0.37
    ען
    0.36
     intertw
    0.35
     पत्रकार
    0.35
     reqParams
    0.35
    ">—
    0.35
    Activations Density 0.012%

    No Known Activations