© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14738
    Prev
    Next
    INDEX
    Explanations

    radioactive waste and isotopes

    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_15_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
     कंप
    0.43
    {
    0.42
    тивний
    0.40
    iliter
    0.38
    land
    0.38
     큰
    0.37
     ("
    0.36
     Biology
    0.36
    юй
    0.36
     人
    0.36
    POSITIVE LOGITS
     behest
    0.45
    鈾
    0.45
    ఆర్
    0.39
    紘
    0.38
     odst
    0.38
    が行
    0.38
    Dur
    0.37
    Excel
    0.37
    рел
    0.37
    uminação
    0.37
    Activations Density 0.018%

    No Known Activations