© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216245
    Prev
    Next
    INDEX
    Explanations

    Matt/Matthew names

    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
     ví
    0.44
    Bracketing
    0.43
     তন্ম
    0.41
     subtract
    0.39
     pseud
    0.39
    เวล
    0.39
     subtracted
    0.39
    (../
    0.38
    вле
    0.38
     Subtract
    0.37
    POSITIVE LOGITS
     DW
    0.42
    Dm
    0.41
    DW
    0.41
    Dw
    0.38
     heap
    0.38
     dv
    0.37
     Eber
    0.37
    dU
    0.36
    achine
    0.36
     deutsche
    0.36
    Activations Density 0.000%

    No Known Activations