© 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. 219827
    Prev
    Next
    INDEX
    Explanations

    Thank you, Optional, Absent

    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
     horas
    0.48
     godziny
    0.46
     hours
    0.46
     pomeriggio
    0.43
    旪
    0.42
     godzin
    0.41
     часа
    0.41
    hours
    0.41
     Hours
    0.40
     часу
    0.40
    POSITIVE LOGITS
    譁
    0.40
    నులు
    0.37
     Sulawesi
    0.36
     его
    0.36
     ച
    0.35
    षक
    0.35
    하려면
    0.35
     campers
    0.34
     triumphant
    0.34
    해
    0.34
    Activations Density 0.018%

    No Known Activations