© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201617
    Prev
    Next
    INDEX
    Explanations

    Sverre, verdrup, wild

    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_37_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
     zák
    0.36
    buds
    0.36
    ⵏ
    0.36
     inability
    0.35
     Outback
    0.35
     admirably
    0.34
     kinet
    0.34
     IPTV
    0.34
     wrongly
    0.34
     उपकरणों
    0.34
    POSITIVE LOGITS
    ITLE
    0.41
    esto
    0.40
    滯
    0.39
     esto
    0.38
    ugan
    0.38
    kos
    0.36
    italia
    0.36
    idal
    0.36
    档
    0.36
    ួល
    0.36
    Activations Density 0.001%

    No Known Activations