© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210531
    Prev
    Next
    INDEX
    Explanations

    INS followed by a word

    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
    ш
    1.29
    의
    1.27
    ש
    1.24
    の
    1.20
    ش
    1.13
    д
    1.10
    기
    1.10
    ’
    1.08
    ૨
    1.08
    ೨
    1.08
    POSITIVE LOGITS
    ى
    1.45
    at
    1.20
    f
    1.11
    ors
    1.07
    e
    1.02
    es
    0.99
    jeni
    0.92
    europe
    0.91
    er
    0.91
    orno
    0.90
    Activations Density 0.001%

    No Known Activations