© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40597
    Prev
    Next
    INDEX
    Explanations

    human action cost

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    >{
    0.64
    в
    0.61
     cataly
    0.58
    }+{\
    0.56
    َح
    0.55
    }>{
    0.55
    দের
    0.55
     Iod
    0.54
    }={
    0.54
     Staub
    0.54
    POSITIVE LOGITS
    r
    0.89
    l
    0.89
    a
    0.84
    d
    0.77
    t
    0.75
    i
    0.75
    an
    0.72
    m
    0.68
    h
    0.65
    al
    0.64
    Activations Density 0.007%

    No Known Activations