© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258544
    Prev
    Next
    INDEX
    Explanations

    code blocks and structure delimiters

    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_22_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
     двух
    0.45
     тези
    0.43
    吒
    0.42
     два
    0.41
     тебя
    0.41
     записа
    0.41
    akel
    0.40
     keresztül
    0.40
    akarta
    0.39
    циона
    0.39
    POSITIVE LOGITS
    مركز
    0.44
    გ
    0.43
    getBase
    0.42
     ორგან
    0.41
    迺
    0.41
    Հ
    0.40
    produksi
    0.40
     गिरि
    0.40
    ر
    0.39
    وع
    0.39
    Activations Density 0.000%

    No Known Activations