© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181977
    Prev
    Next
    INDEX
    Explanations

    large portions, excessive amounts

    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
     العدد
    0.39
    卍
    0.37
    ป์
    0.36
     compaction
    0.35
     Saddam
    0.35
     excesses
    0.34
     surpluses
    0.34
     ENGINEERS
    0.34
    酬
    0.34
     حاجه
    0.34
    POSITIVE LOGITS
     retr
    0.38
    cante
    0.38
     digit
    0.38
     rating
    0.37
    punt
    0.37
    क्ति
    0.36
     lent
    0.36
    fusc
    0.35
     evidente
    0.35
     atract
    0.35
    Activations Density 0.001%

    No Known Activations