© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34922
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     JH
    0.46
     Ma
    0.43
     Hendrick
    0.42
    濮
    0.42
    JH
    0.40
     purge
    0.39
     JMS
    0.39
    च्छेद
    0.38
    λαβ
    0.38
     maid
    0.38
    POSITIVE LOGITS
     കമ
    0.45
    INO
    0.40
    Cam
    0.39
    Campo
    0.39
    Al
    0.36
     لكم
    0.36
    unting
    0.36
    িকাংশ
    0.36
    薩
    0.36
    oursquare
    0.36
    Activations Density 0.002%

    No Known Activations