© 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. 85318
    Prev
    Next
    INDEX
    Explanations

    blocksworld problems

    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
    ,
    0.78
     yarns
    0.66
     aler
    0.65
    :
    0.63
     rhymes
    0.63
     emotes
    0.63
     vests
    0.62
     alerts
    0.60
     evidences
    0.60
     respondents
    0.58
    POSITIVE LOGITS
    <0x80>
    0.69
    with
    0.58
    ५
    0.57
    OS
    0.55
    cpy
    0.55
    vì
    0.55
    för
    0.54
    AY
    0.53
    <0xAB>
    0.52
    0.51
    Activations Density 0.015%

    No Known Activations