© 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. 108925
    Prev
    Next
    INDEX
    Explanations

    propensity score, model, unhealthy

    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
    ps
    1.60
    la
    1.55
    d
    1.55
    b
    1.54
    x
    1.54
    lar
    1.49
    the
    1.45
    link
    1.32
    ning
    1.30
    un
    1.28
    POSITIVE LOGITS
    ى
    1.57
    ру
    1.50
    ем
    1.42
    ０
    1.39
    ти
    1.38
    ۰
    1.24
    ט
    1.23
    <0x80>
    1.18
    ্ডার
    1.10
     urmă
    1.07
    Activations Density 0.000%

    No Known Activations