© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9990
    Prev
    Next
    INDEX
    Explanations

    hub for logistic importance

    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_13_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
    soft
    0.60
    sp
    0.57
    og
    0.57
    krét
    0.56
    od
    0.55
    um
    0.55
    swift
    0.54
    x
    0.54
    ad
    0.54
    御
    0.54
    POSITIVE LOGITS
     deuxième
    0.61
     IST
    0.57
     day
    0.57
     navigateur
    0.55
     séries
    0.55
    <strong>
    0.55
     suspicion
    0.55
     navigator
    0.55
     logistic
    0.55
     atan
    0.55
    Activations Density 0.038%

    No Known Activations