© 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. 176523
    Prev
    Next
    INDEX
    Explanations

    Greetings and short phrases

    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
    푚
    0.41
    ່ມ
    0.40
     ناج
    0.39
     moment
    0.39
     dover
    0.38
     ping
    0.37
     dong
    0.37
    伺
    0.37
     mest
    0.37
     ιδια
    0.37
    POSITIVE LOGITS
    une
    0.44
    COS
    0.43
    Hai
    0.43
     Sampling
    0.42
     Cos
    0.42
     Hai
    0.41
    Al
    0.40
     al
    0.39
    hai
    0.39
    Cos
    0.39
    Activations Density 0.000%

    No Known Activations