© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154330
    Prev
    Next
    INDEX
    Explanations

    Ever

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    INDOW
    0.45
     needs
    0.43
     Kxb
    0.39
    Given
    0.37
    Needs
    0.36
    halter
    0.36
    Rack
    0.36
    堂
    0.36
    Pair
    0.36
    tod
    0.36
    POSITIVE LOGITS
    ствуют
    0.51
     hacen
    0.46
    integrate
    0.43
     Jim
    0.43
     Running
    0.41
     fanno
    0.41
     fazem
    0.41
    ırlar
    0.40
     aumenta
    0.40
    щают
    0.40
    Activations Density 0.000%

    No Known Activations