© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5848
    Prev
    Next
    INDEX
    Explanations

    federally recognized tribes

    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_40_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
    certs
    0.38
     سن
    0.35
    选中
    0.35
    𒌷
    0.35
     icch
    0.35
     nonEmpty
    0.35
     zest
    0.34
    汽
    0.34
    财产
    0.34
    tolist
    0.33
    POSITIVE LOGITS
     band
    1.36
     bands
    1.24
    band
    1.22
     Band
    1.20
    bands
    1.19
    Band
    1.18
     banda
    1.13
     BAND
    1.12
     Bands
    1.11
    BAND
    1.09
    Activations Density 0.027%

    No Known Activations