© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235395
    Prev
    Next
    INDEX
    Explanations

    say "filepath"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ёр
    0.40
     service
    0.39
     राजन
    0.39
     *@
    0.39
    illon
    0.39
    的所有
    0.38
     trek
    0.38
    îte
    0.37
    *=
    0.37
    wort
    0.37
    POSITIVE LOGITS
     chúng
    0.41
    Occasionally
    0.39
    Chúng
    0.37
     penuh
    0.36
     श्रॉफ
    0.35
     Nós
    0.35
     我们
    0.35
    inputType
    0.35
    पीसी
    0.34
    стно
    0.34
    Activations Density 0.004%

    No Known Activations