© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31612
    Prev
    Next
    INDEX
    Explanations

    about to happen

    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_31_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
    꽤
    0.39
     acog
    0.37
     sanitario
    0.37
    칩
    0.37
     difficulties
    0.36
     महान
    0.35
     troubles
    0.35
     ir
    0.35
     preoccupation
    0.34
    玥
    0.34
    POSITIVE LOGITS
    即将
    0.63
     slated
    0.55
     предстоя
    0.51
    ที่จะ
    0.47
    ToSend
    0.46
     sắp
    0.45
     gonna
    0.44
    zuführen
    0.43
    要去
    0.43
     să
    0.42
    Activations Density 0.002%

    No Known Activations