© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35799
    Prev
    Next
    INDEX
    Explanations

    Gom, omer, compre

    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_3_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
    。
    0.84
    ।
    0.73
    mal
    0.68
    。"
    0.64
     οπο
    0.64
    。[
    0.61
    。(
    0.60
     (
    0.59
    ج
    0.58
    𝙧
    0.58
    POSITIVE LOGITS
    ות
    0.88
    er
    0.86
    s
    0.79
    ર
    0.77
    ര
    0.77
    ς
    0.77
    ים
    0.74
    ИС
    0.73
    ો
    0.69
    ر
    0.68
    Activations Density 0.005%

    No Known Activations