© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14179
    Prev
    Next
    INDEX
    Explanations

    pairs of 3 or [3,3]

    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_40_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
    عيد
    0.39
    悠
    0.36
    澳门
    0.36
    不再
    0.35
    قات
    0.35
    ذیر
    0.35
     بلا
    0.34
     атрибу
    0.33
    ुक
    0.33
    愉
    0.33
    POSITIVE LOGITS
    녈
    0.42
    ಾವ್
    0.40
     стаби
    0.40
     سلطان
    0.39
    ernen
    0.38
    ²',
    0.38
    でき
    0.36
    ContentLoaded
    0.36
    stability
    0.35
    เช่น
    0.35
    Activations Density 0.000%

    No Known Activations