© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217634
    Prev
    Next
    INDEX
    Explanations

    nasa climat.gov PBN Approach

    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_16_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
    される
    0.53
    ことができる
    0.51
    ありません
    0.50
    া
    0.50
     Raila
    0.49
    主力
    0.49
    岳
    0.48
    ા
    0.48
     Value
    0.46
     uchun
    0.45
    POSITIVE LOGITS
    sk
    0.53
    path
    0.51
    pre
    0.50
    bes
    0.49
    ry
    0.47
    te
    0.47
     path
    0.46
    cin
    0.45
     IMS
    0.44
    те
    0.44
    Activations Density 0.000%

    No Known Activations