© 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. 6260
    Prev
    Next
    INDEX
    Explanations

    particles like 'de'

    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
    鈽
    0.42
    防控
    0.40
    فاع
    0.40
    풉
    0.40
    正規
    0.40
    েন্ত্র
    0.40
    を変更
    0.39
    ]}/
    0.39
    Officials
    0.39
    ྩ
    0.39
    POSITIVE LOGITS
     Khan
    0.43
     location
    0.40
     va
    0.39
     Comrade
    0.39
     Mecca
    0.39
     Genesis
    0.38
     per
    0.38
     ka
    0.38
     indu
    0.38
     fiber
    0.38
    Activations Density 0.033%

    No Known Activations