© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16991
    Prev
    Next
    INDEX
    Explanations

    based

    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_15_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
    :
    0.51
    le
    0.49
    :“
    0.48
    -:
    0.47
    寮
    0.47
    worth
    0.46
    လုံး
    0.46
    man
    0.44
     called
    0.44
    稱為
    0.44
    POSITIVE LOGITS
    Pued
    0.50
     deben
    0.48
    Monte
    0.47
    俳
    0.47
    Как
    0.46
     doivent
    0.45
     مسلمانوں
    0.42
    翠
    0.42
     Vito
    0.41
    Та
    0.41
    Activations Density 0.000%

    No Known Activations