© 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. 32804
    Prev
    Next
    INDEX
    Explanations

    cul

    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
    ย์
    0.43
    身
    0.42
     Irwin
    0.40
     Erwin
    0.37
    chdir
    0.37
    客
    0.36
    ющих
    0.36
    潛
    0.36
    opuerto
    0.35
    栗
    0.35
    POSITIVE LOGITS
    unders
    0.45
     доро
    0.40
    служи
    0.40
    vers
    0.39
     Dams
    0.39
     pok
    0.39
     সুল
    0.38
    ℂ
    0.38
    доро
    0.38
    ült
    0.38
    Activations Density 0.000%

    No Known Activations