© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 539
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     дела
    0.88
    ették
    0.88
    =""><
    0.88
    ylvan
    0.85
    ủi
    0.84
     covariance
    0.83
    ುವ
    0.83
    ান্য
    0.82
     શકાય
    0.81
    ından
    0.81
    POSITIVE LOGITS
    ن
    1.22
    ر
    1.11
    на
    0.95
    анд
    0.93
    ب
    0.92
    ૧
    0.91
    ل
    0.89
    ق
    0.88
    ال
    0.87
    ಗ
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.