© 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. 112051
    Prev
    Next
    INDEX
    Explanations

    EAC, UAC, AC

    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
    s
    2.22
    g
    1.39
     I
    1.34
    d
    1.27
    y
    1.23
     to
    1.19
    0
    1.13
    li
    1.11
    a
    1.11
     a
    1.10
    POSITIVE LOGITS
    ра
    1.52
    した
    1.31
    ต์
    1.31
    ко
    1.21
    .}}
    1.16
    ર
    1.12
    것
    1.12
    ческие
    1.11
    й
    1.11
    ിയ
    1.08
    Activations Density 0.001%

    No Known Activations