© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192720
    Prev
    Next
    INDEX
    Explanations

    parentheses or citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    t
    1.54
    an
    1.48
    ت
    1.41
    l
    1.40
    y
    1.37
    v
    1.30
    et
    1.27
    p
    1.27
    el
    1.20
    s
    1.20
    POSITIVE LOGITS
    ﻟ
    1.02
     îi
    0.96
     i
    0.90
    ۰
    0.89
     همچنین
    0.89
     riječi
    0.88
     تقویت
    0.88
     забезпечення
    0.88
    お店
    0.87
     punctures
    0.86
    Activations Density 0.015%

    No Known Activations