© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38603
    Prev
    Next
    INDEX
    Explanations

    quantities of repetition

    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_11_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
    Didn
    0.61
    arquivo
    0.57
    A
    0.57
    q
    0.56
    did
    0.53
    currentPage
    0.53
    dfs
    0.52
    Parameter
    0.52
    pcs
    0.52
    District
    0.50
    POSITIVE LOGITS
     sonar
    0.63
     madam
    0.59
     beho
    0.57
     ук
    0.57
     erasing
    0.57
    ☔
    0.56
     whirlpool
    0.55
    😍😍
    0.55
     визнача
    0.55
     mogul
    0.55
    Activations Density 0.018%

    No Known Activations