© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171792
    Prev
    Next
    INDEX
    Explanations

    fall into black holes

    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_20_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
    tena
    0.42
     talisman
    0.42
    菈
    0.42
    getSession
    0.41
    ais
    0.41
     Thessalon
    0.41
    ès
    0.40
     Retro
    0.40
    🧛
    0.39
    لاً
    0.39
    POSITIVE LOGITS
    余
    0.43
    कांत
    0.41
     गिरावट
    0.40
    Freeman
    0.40
    IOR
    0.39
     shove
    0.39
     foreground
    0.39
    станов
    0.38
    marking
    0.38
    Jenkins
    0.38
    Activations Density 0.000%

    No Known Activations