© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78242
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and attributes

    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_31_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
     scab
    0.38
    ẖ
    0.37
    heritage
    0.37
     ئەو
    0.37
    Cro
    0.36
    Leaders
    0.36
    优质
    0.35
    世
    0.35
    istosoma
    0.35
     ganglions
    0.34
    POSITIVE LOGITS
    κών
    0.41
     অন্ধকার
    0.40
     involve
    0.37
     infinite
    0.36
     SplashScreen
    0.36
     involvement
    0.35
     distractions
    0.35
     причиной
    0.35
     Mobile
    0.35
     वैकल्पिक
    0.34
    Activations Density 0.000%

    No Known Activations