© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91569
    Prev
    Next
    INDEX
    Explanations

    live

    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
     жи
    1.26
    Living
    1.21
     Living
    1.09
     living
    1.05
    Live
    1.05
    living
    1.05
     živ
    1.04
    活
    1.00
     ży
    1.00
     LIVING
    0.97
    POSITIVE LOGITS
     oxidative
    0.57
     argumentative
    0.55
     Descriptive
    0.53
     descriptive
    0.52
     aggressively
    0.49
     reflective
    0.48
     declaratory
    0.48
     declarative
    0.46
     meditative
    0.46
     operative
    0.46
    Activations Density 0.001%

    No Known Activations