© 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. 1674
    Prev
    Next
    INDEX
    Explanations

    authors of books

    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
     computationally
    0.52
     computational
    0.44
     Computational
    0.43
    Computational
    0.40
    comput
    0.38
    Comput
    0.37
    大切
    0.37
    ઈ
    0.36
     attended
    0.36
     Schnitt
    0.36
    POSITIVE LOGITS
     renewal
    0.42
     Renewal
    0.39
     renewing
    0.38
     renewals
    0.38
     indag
    0.36
     ritual
    0.35
     exist
    0.35
     मोटर
    0.35
    न्द्र
    0.35
     reopen
    0.35
    Activations Density 0.020%

    No Known Activations