© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136803
    Prev
    Next
    INDEX
    Explanations

    Oder, oder, or

    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_12_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
     convexe
    0.54
     takie
    0.54
     funcionar
    0.51
     Temperatura
    0.50
     şi
    0.49
     Funktion
    0.49
     funcional
    0.49
    ்
    0.49
     ใช้
    0.49
    EndInit
    0.48
    POSITIVE LOGITS
    ation
    0.59
    credited
    0.59
    atories
    0.54
    acles
    0.53
    ableness
    0.52
    çado
    0.52
     यूं
    0.51
    hold
    0.50
    روس
    0.50
    سل
    0.49
    Activations Density 0.002%

    No Known Activations