© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133189
    Prev
    Next
    INDEX
    Explanations

    anxiety or accustomed

    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_1_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
    은
    1.33
    that
    1.30
    지만
    1.30
    the
    1.14
    2
    1.13
    は
    1.12
    مع
    1.09
    지
    1.08
    she
    1.04
    น
    1.03
    POSITIVE LOGITS
    er
    1.16
     for
    1.11
    erin
    1.09
    eris
    1.05
    erne
    1.04
    eran
    0.98
    el
    0.95
    erat
    0.95
    et
    0.95
    ek
    0.94
    Activations Density 0.012%

    No Known Activations