© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143975
    Prev
    Next
    INDEX
    Explanations

    server

    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_0_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
    1.35
    I
    1.27
    -
    1.12
    к
    1.11
     l
    1.03
     (
    1.03
     $
    1.02
     router
    0.98
     DVD
    0.98
    )$
    0.96
    POSITIVE LOGITS
    ب
    1.70
    it
    1.43
    ו
    1.41
    ي
    1.39
    ين
    1.38
    d
    1.34
    مي
    1.34
    اك
    1.33
    عين
    1.30
     nó
    1.30
    Activations Density 0.001%

    No Known Activations