© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60806
    Prev
    Next
    INDEX
    Explanations

    breakdown

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     my
    0.56
    ":
    0.46
    all
    0.46
     setting
    0.46
    my
    0.45
    :"
    0.44
    Setting
    0.44
    setting
    0.43
    ':
    0.42
     Setting
    0.42
    POSITIVE LOGITS
     अगस्त
    0.46
     Focusing
    0.44
     Ге
    0.43
     Happens
    0.43
     DA
    0.39
     јуну
    0.39
     =)
    0.39
     happens
    0.38
     происходит
    0.38
     At
    0.38
    Activations Density 0.008%

    No Known Activations