© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177144
    Prev
    Next
    INDEX
    Explanations

    quantities and time

    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_50_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
     :,
    0.46
     ;,
    0.43
     terraces
    0.41
     Nusantara
    0.39
    :,
    0.38
    🫦
    0.37
     Hun
    0.37
    UMBIA
    0.37
     کول
    0.36
     Meghna
    0.36
    POSITIVE LOGITS
    eming
    0.40
     Nee
    0.38
    ewo
    0.38
    ipe
    0.37
    हाय
    0.37
     Keys
    0.37
    oti
    0.36
    Ⅽ
    0.36
    edes
    0.36
    platin
    0.35
    Activations Density 0.001%

    No Known Activations