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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38773
    Prev
    Next
    INDEX
    Explanations

    defined by what someone/something is not

    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_11_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
     अत्य
    0.60
    ן
    0.57
     சார்ந்த
    0.56
    λου
    0.56
    ﻰ
    0.55
     معرض
    0.55
    ರುತ್ತದೆ
    0.54
     groupe
    0.52
    chehen
    0.52
    ﻲ
    0.52
    POSITIVE LOGITS
     chua
    0.63
     Drainage
    0.56
     Till
    0.55
     upang
    0.54
     Gemeinde
    0.53
     Morphology
    0.53
     hatırl
    0.52
     voordat
    0.52
     church
    0.51
     sawa
    0.51
    Activations Density 0.007%

    No Known Activations