© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26986
    Prev
    Next
    INDEX
    Explanations

    Montgomery Bus Boycott

    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
    穀
    0.42
    煙
    0.42
     Какие
    0.41
    werpen
    0.40
     foams
    0.39
    绸
    0.39
    ravi
    0.38
     Foam
    0.38
    たつ
    0.38
    賽
    0.37
    POSITIVE LOGITS
     Montgomery
    0.73
    Montgomery
    0.72
    Rosa
    0.55
    Bus
    0.51
    Mont
    0.51
     Rosa
    0.51
    Parks
    0.51
     bus
    0.50
     Mont
    0.50
     MONT
    0.49
    Activations Density 0.018%

    No Known Activations