© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5626
    Prev
    Next
    INDEX
    Explanations

    border:

    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
     phosphorus
    0.31
     humus
    0.30
    ±
    0.30
     pied
    0.29
    orean
    0.28
     Sche
    0.28
    ITLE
    0.28
     testo
    0.28
     multiuser
    0.28
    {\$
    0.28
    POSITIVE LOGITS
    AIRE
    0.29
     پایین
    0.29
     грани
    0.29
    Confidence
    0.29
    Mission
    0.29
    稗
    0.29
     broadening
    0.28
    dispatcher
    0.28
    <0xB7>
    0.28
    Respiratory
    0.28
    Activations Density 0.000%

    No Known Activations