© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31726
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_31_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
     least
    0.38
     Acute
    0.35
     예배
    0.34
     HCC
    0.34
     ук
    0.34
    least
    0.34
     شكل
    0.33
     ኩ
    0.33
    性質
    0.33
     constitut
    0.33
    POSITIVE LOGITS
    anshi
    0.40
    捷
    0.39
     estaciones
    0.36
    心理
    0.36
    ப்புகளில்
    0.35
    Free
    0.35
    {[\
    0.35
     shoot
    0.34
     Technologien
    0.34
    eal
    0.34
    Activations Density 0.075%

    No Known Activations