© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252001
    Prev
    Next
    INDEX
    Explanations

    requests

    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
     dando
    0.42
     error
    0.42
     চিকিৎ
    0.41
     defining
    0.41
     transmitting
    0.40
     synthesizing
    0.40
     treating
    0.39
     ł
    0.39
     Defining
    0.39
     declaring
    0.39
    POSITIVE LOGITS
    Heb
    0.55
    ヘ
    0.54
    uran
    0.52
    ure
    0.50
    urar
    0.50
    Heap
    0.50
     Heidelberg
    0.49
    हे
    0.49
    হে
    0.48
    UR
    0.48
    Activations Density 0.000%

    No Known Activations