© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162384
    Prev
    Next
    INDEX
    Explanations

    getting defensive

    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
    える
    1.14
    ні
    1.13
    2
    1.08
    ూ
    1.01
    いる
    0.98
    ม
    0.97
    정이
    0.94
    ู
    0.94
    ет
    0.92
    ט
    0.91
    POSITIVE LOGITS
    a
    2.23
    ت
    1.83
    in
    1.41
    i
    1.40
    ה
    1.40
    an
    1.36
    ه
    1.26
    at
    1.25
    יות
    1.25
    n
    1.25
    Activations Density 0.001%

    No Known Activations