© 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. 81045
    Prev
    Next
    INDEX
    Explanations

    TES=

    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
    لي
    1.34
    <0x80>
    1.15
    z
    1.13
    j
    1.08
     públicos
    1.05
    ce
    0.98
    nelles
    0.96
    zego
    0.96
    haha
    0.96
    tra
    0.95
    POSITIVE LOGITS
    ון
    1.60
    ным
    1.59
    у
    1.43
    س
    1.43
    ने
    1.41
    یت
    1.37
    า
    1.37
    8
    1.36
    с
    1.32
    ก
    1.31
    Activations Density 0.004%

    No Known Activations