© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134290
    Prev
    Next
    INDEX
    Explanations

    basic

    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_6_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
    قوم
    0.86
    منا
    0.82
    مون
    0.80
    قف
    0.80
    ق
    0.79
    Cursor
    0.78
    س
    0.77
    نز
    0.77
    Screen
    0.77
     మన
    0.77
    POSITIVE LOGITS
    ي
    1.46
    ле
    1.38
    i
    1.19
    á
    1.13
     adolescente
    1.06
    т
    1.05
     fruitless
    1.02
    。
    1.01
     estará
    1.00
    ಗೊಂಡ
    1.00
    Activations Density 0.000%

    No Known Activations