© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66983
    Prev
    Next
    INDEX
    Explanations

    again, afterwards, then

    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_41_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
    ยาง
    0.37
     ለአ
    0.36
    ＇
    0.36
     total
    0.36
    徳
    0.35
     eventdata
    0.35
    अभ
    0.35
     dovet
    0.35
     nucleus
    0.35
    ธอ
    0.34
    POSITIVE LOGITS
    再说
    0.91
    ค่อย
    0.87
    再
    0.75
    再來
    0.68
    再去
    0.66
     再
    0.55
    然后再
    0.55
     slowly
    0.50
    后再
    0.50
    してから
    0.47
    Activations Density 0.015%

    No Known Activations