© 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. 249360
    Prev
    Next
    INDEX
    Explanations

    referring

    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
    es
    0.41
    ev
    0.40
    o
    0.40
    eing
    0.39
    e
    0.39
    oshape
    0.39
    ec
    0.38
    polis
    0.37
    ീ
    0.37
    Φ
    0.36
    POSITIVE LOGITS
     rá
    0.59
    rà
    0.59
     ră
    0.58
    razioni
    0.57
    rao
    0.56
    rá
    0.55
     র‍
    0.54
    rala
    0.51
    ρά
    0.50
     র‌
    0.50
    Activations Density 0.001%

    No Known Activations