© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2471
    Prev
    Next
    INDEX
    Explanations

    reach out for help

    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_39_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
    зей
    0.38
    很重要
    0.37
    jela
    0.35
    ձ
    0.35
     elif
    0.35
    ্কে
    0.34
    らす
    0.34
     fieldContext
    0.33
    しも
    0.33
    カイ
    0.33
    POSITIVE LOGITS
    ゅ
    0.52
    lamydia
    0.44
    ätzung
    0.40
    neider
    0.38
    ildren
    0.38
    loride
    0.38
    ኋ
    0.38
    sure
    0.37
    ിത്ര
    0.37
    鸹
    0.36
    Activations Density 0.095%

    No Known Activations