© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107926
    Prev
    Next
    INDEX
    Explanations

    alba, alte, ALR, Allegra, Alyeska

    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_2_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
    ן
    1.75
    ิ
    1.51
    ной
    1.48
    <0x80>
    1.30
    0
    1.30
    ู
    1.30
    я
    1.27
    ี
    1.23
     presion
    1.14
    дер
    1.13
    POSITIVE LOGITS
    la
    1.59
    一
    1.37
    我
    1.33
    d
    1.32
    大
    1.26
    这
    1.15
    上
    1.13
    あ
    1.09
    ل
    1.09
    ll
    1.08
    Activations Density 0.001%

    No Known Activations