© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50971
    Prev
    Next
    INDEX
    Explanations

    how often

    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
    ਭ
    0.38
    ـــ
    0.36
    葺
    0.36
     máquinas
    0.35
     추진
    0.34
    rash
    0.34
    ťa
    0.33
    দো
    0.33
     yad
    0.33
    ــ
    0.32
    POSITIVE LOGITS
     frequently
    0.86
     frequ
    0.82
     frequent
    0.81
    頻
    0.80
     frequentemente
    0.79
     frecu
    0.77
     Frequently
    0.76
     fréquemment
    0.75
    Frequently
    0.73
     frecuentes
    0.72
    Activations Density 0.000%

    No Known Activations