© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 218336
    Prev
    Next
    INDEX
    Explanations

    move away or step outside

    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_31_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
    赘
    0.38
     stump
    0.36
    杳
    0.36
    <unused93>
    0.36
     shaved
    0.35
     stupe
    0.35
    Spawn
    0.35
    瑶
    0.35
    Rational
    0.35
     नियोजन
    0.35
    POSITIVE LOGITS
     antidote
    0.38
    หน
    0.38
     Boeh
    0.38
    ர
    0.38
     volumetric
    0.37
    microwave
    0.37
     እንኳ
    0.37
    rotor
    0.37
     volume
    0.36
     microwave
    0.36
    Activations Density 0.006%

    No Known Activations