© 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. 158912
    Prev
    Next
    INDEX
    Explanations

    family members

    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
    фро
    0.46
    NORE
    0.42
    尣
    0.38
    িয়েছেন
    0.37
     personales
    0.36
     بات
    0.36
    нного
    0.36
     zee
    0.36
    社区
    0.36
    覂
    0.36
    POSITIVE LOGITS
    调
    0.43
     embod
    0.41
    調
    0.41
     調
    0.40
     bearing
    0.38
    leqq
    0.37
    icis
    0.37
     embody
    0.37
     customise
    0.37
     chirp
    0.36
    Activations Density 0.001%

    No Known Activations