© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92625
    Prev
    Next
    INDEX
    Explanations

    '

    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_60_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
     ;
    0.57
     facilitate
    0.49
     ;;
    0.48
     ;\
    0.48
     much
    0.48
    much
    0.47
     bring
    0.42
     muchísimo
    0.41
     apply
    0.41
     revitalize
    0.41
    POSITIVE LOGITS
    S
    0.67
    ll
    0.59
    sst
    0.50
    s
    0.48
    sg
    0.47
    sp
    0.46
    ryn
    0.46
    sto
    0.45
    hme
    0.45
    sG
    0.45
    Activations Density 0.033%

    No Known Activations