© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211825
    Prev
    Next
    INDEX
    Explanations

    lock or brok endings

    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_5_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
    in
    1.41
    ার্স
    1.17
    u
    1.16
    რების
    1.16
    ोली
    1.12
    لية
    1.12
    یع
    1.08
    inę
    1.07
    ו
    1.07
    ロ
    1.06
    POSITIVE LOGITS
    '
    1.62
    v
    1.14
    ↵
    1.05
    c
    1.04
    of
    1.00
     That
    0.95
    b
    0.90
    {
    0.90
     changement
    0.89
    ni
    0.87
    Activations Density 0.000%

    No Known Activations