© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 80942
    Prev
    Next
    INDEX
    Explanations

    mischaracterization, bullshit, imagined, not what they said, don't you understand, you wouldn't understand

    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_29_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
     hiz
    0.33
     allevi
    0.33
     dhamme
    0.31
    !="
    0.31
     TRANSM
    0.30
    継
    0.30
     schoon
    0.30
     [['
    0.30
    ؎
    0.30
    azem
    0.29
    POSITIVE LOGITS
    圈
    0.31
    radas
    0.30
    dinner
    0.30
     cenas
    0.30
     endless
    0.29
     जताई
    0.28
    宴
    0.28
     apparently
    0.27
    aping
    0.27
     Libraries
    0.27
    Activations Density 0.004%

    No Known Activations