© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200413
    Prev
    Next
    INDEX
    Explanations

    Rapid

    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_50_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
    great
    0.41
     great
    0.38
    diagn
    0.36
     Feuilles
    0.36
     דער
    0.36
    olol
    0.35
    Ә
    0.35
     तुम्हारा
    0.35
    aturated
    0.34
    тельный
    0.34
    POSITIVE LOGITS
    ᆻ
    0.41
     segmental
    0.39
     vp
    0.39
    zogen
    0.38
    athing
    0.37
    ッティング
    0.36
     noticing
    0.35
    ctomy
    0.35
     playback
    0.35
     velocidades
    0.35
    Activations Density 0.004%

    No Known Activations