© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159851
    Prev
    Next
    INDEX
    Explanations

    IRT, architecture, iendo

    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
    ש
    1.31
     a
    1.20
    ться
    1.08
    お手
    1.05
     а
    1.02
    ल
    1.01
    あり
    1.00
     reshaping
    0.96
    ມີ
    0.95
    こちらの
    0.94
    POSITIVE LOGITS
    a
    1.32
     for
    1.24
    an
    1.20
    ed
    1.18
    ag
    1.18
    ва
    1.16
    ان
    1.11
    ul
    1.09
    াৰ
    1.05
    o
    1.01
    Activations Density 0.001%

    No Known Activations