© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243783
    Prev
    Next
    INDEX
    Explanations

    If you are experiencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    ቆዳ
    0.39
    ponenten
    0.38
    ிலை
    0.37
    Vir
    0.36
    quire
    0.36
    Tarea
    0.36
     کاربر
    0.36
    ք
    0.35
     Vir
    0.35
    viper
    0.34
    POSITIVE LOGITS
     refuge
    0.42
     pad
    0.41
     github
    0.39
     seeking
    0.38
    egra
    0.38
     télé
    0.37
     empieza
    0.37
     FutureWarning
    0.37
     retreat
    0.36
     zaj
    0.36
    Activations Density 0.005%

    No Known Activations