© 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. 250890
    Prev
    Next
    INDEX
    Explanations

    Tang Dynasty

    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
     eup
    0.38
     لن
    0.38
     sampling
    0.37
     evitar
    0.37
     internalized
    0.36
     escalar
    0.36
    앙
    0.36
     veditabbo
    0.36
    obbly
    0.36
    ⓓ
    0.35
    POSITIVE LOGITS
    s
    0.64
    Roman
    0.51
     Roman
    0.50
    Rim
    0.46
    sons
    0.45
    roman
    0.44
     roman
    0.44
    罗马
    0.43
    Romans
    0.43
    ogad
    0.43
    Activations Density 0.000%

    No Known Activations