© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204671
    Prev
    Next
    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     chúng
    0.46
     Chúng
    0.42
     pairings
    0.42
     we
    0.42
     FIRST
    0.41
     мы
    0.41
     เรา
    0.40
     +,
    0.39
     우리는
    0.39
     نحن
    0.39
    POSITIVE LOGITS
     find
    0.46
     finds
    0.40
    find
    0.39
     Find
    0.38
    Find
    0.38
    ímica
    0.38
    Could
    0.37
    Opposition
    0.37
     set
    0.37
    Will
    0.36
    Activations Density 0.002%

    No Known Activations