© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81694
    Prev
    Next
    INDEX
    Explanations

    needed something

    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_0_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
    ية
    2.36
    و
    2.06
    ו
    1.90
    то
    1.80
    َ
    1.63
    י
    1.55
     to
    1.54
    다
    1.52
     be
    1.50
    и
    1.48
    POSITIVE LOGITS
    iv
    1.54
    v
    1.37
    for
    1.36
    ↵↵
    1.30
    av
    1.24
    3
    1.18
    avimo
    1.16
    H
    1.10
    B
    1.09
    T
    1.06
    Activations Density 0.000%

    No Known Activations