© 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. 180353
    Prev
    Next
    INDEX
    Explanations

    This is followed by a problem description

    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
     bè
    0.38
    ༣
    0.38
    йтесь
    0.37
    TEL
    0.37
    锯
    0.37
    єте
    0.37
     Сасик
    0.37
    <0x07>
    0.36
     ট্র
    0.36
     расти
    0.36
    POSITIVE LOGITS
     supposedly
    0.41
     engender
    0.40
     purportedly
    0.40
     )-
    0.37
     suppression
    0.36
     allegedly
    0.35
     Compton
    0.35
     accompanied
    0.34
     supabase
    0.34
     Seems
    0.33
    Activations Density 0.002%

    No Known Activations