© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49875
    Prev
    Next
    INDEX
    Explanations

    Facebook research

    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_55_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
     william
    0.45
     tari
    0.36
     Scotland
    0.35
     ע
    0.35
    arlin
    0.35
     ReLU
    0.35
     landlab
    0.35
     Pride
    0.35
    oku
    0.34
     u
    0.34
    POSITIVE LOGITS
     инфраструк
    0.44
    common
    0.41
    業
    0.38
     Tiểu
    0.37
    NumberOperation
    0.37
    実践
    0.37
    colormap
    0.37
    ヘ
    0.36
    bye
    0.36
    愔
    0.36
    Activations Density 0.000%

    No Known Activations