© 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. 151040
    Prev
    Next
    INDEX
    Explanations

    Experience, Monitor

    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
     for
    0.61
    for
    0.59
    是
    0.49
     هو
    0.43
    aid
    0.42
    a
    0.42
     собствен
    0.41
    은
    0.41
     है
    0.41
     is
    0.40
    POSITIVE LOGITS
    Qu
    0.65
    Experience
    0.61
     Experience
    0.59
     Qu
    0.59
    Monitor
    0.58
     stopping
    0.58
    Light
    0.57
     Monitor
    0.56
     Light
    0.55
     एक्सपीरियंस
    0.53
    Activations Density 0.000%

    No Known Activations