© 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. 214349
    Prev
    Next
    INDEX
    Explanations

    company 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
     oss
    0.44
    strand
    0.42
    Dos
    0.40
    oss
    0.40
    GFR
    0.40
    尕
    0.40
     লন্ড
    0.39
     অপু
    0.38
    しょう
    0.37
     Gj
    0.37
    POSITIVE LOGITS
     Rick
    0.50
     Y
    0.49
     Hare
    0.45
    Rick
    0.44
     Yu
    0.41
    𝗬
    0.38
    Hare
    0.38
     Yun
    0.38
     ecclesiastical
    0.37
    uninstall
    0.37
    Activations Density 0.011%

    No Known Activations