© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 173398
    Prev
    Next
    INDEX
    Explanations

    asking for more details or suggestions

    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_20_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
     KAHN
    0.50
    Hasher
    0.49
     hergestellt
    0.49
     Frisch
    0.49
    埴
    0.48
    HttpDelete
    0.47
    মেয়
    0.47
     prépuce
    0.46
    etzte
    0.46
    <unused84>
    0.46
    POSITIVE LOGITS
     ,
    0.48
    day
    0.47
    iden
    0.44
    laughter
    0.44
     entertainment
    0.42
     I
    0.42
    ld
    0.42
     /*
    0.41
     السلام
    0.41
    ant
    0.41
    Activations Density 0.001%

    No Known Activations