© 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. 156082
    Prev
    Next
    INDEX
    Explanations

    floor

    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
     რა
    0.37
    werking
    0.36
    ร้าง
    0.36
    汾
    0.36
    یں
    0.35
    ิ้น
    0.35
     Likes
    0.35
    藁
    0.35
    ็ด
    0.34
     টাইমস
    0.34
    POSITIVE LOGITS
     tsd
    0.39
     ટે
    0.39
     ಕಾರ
    0.38
    Astr
    0.38
    ref
    0.38
     Tus
    0.38
     Blanch
    0.37
    AssetDiscovery
    0.37
    dac
    0.37
    Angel
    0.37
    Activations Density 0.001%

    No Known Activations