© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18008
    Prev
    Next
    INDEX
    Explanations

    parentheses and lists

    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_34_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
    㖣
    0.48
    ادم
    0.43
    㦣
    0.40
    流入
    0.38
     meaningful
    0.38
    㛺
    0.38
     एडम
    0.37
     Đình
    0.37
    portál
    0.37
    咉
    0.37
    POSITIVE LOGITS
    tasks
    0.40
    no
    0.39
    oon
    0.39
    raft
    0.39
    my
    0.37
    stop
    0.37
     Tus
    0.37
     ఓ
    0.37
    bout
    0.37
    ban
    0.37
    Activations Density 0.025%

    No Known Activations