© 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
    2. Gemma-3-27B-IT
    3. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 54251
    Prev
    Next
    INDEX
    Explanations

    instruction/contextual prompts

    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_30_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
    竟
    0.37
    adelphia
    0.34
     পাচ
    0.33
    ्याल
    0.32
    ्रोल
    0.32
    unik
    0.31
    တဲ့
    0.31
    鈮
    0.31
    Meet
    0.30
     ade
    0.30
    POSITIVE LOGITS
     randomness
    0.41
     rambling
    0.39
     sprinkled
    0.38
     simulate
    0.38
     simulating
    0.37
     strewn
    0.37
     disjoint
    0.36
     wavy
    0.36
     accent
    0.36
    illusion
    0.36
    Activations Density 0.225%

    No Known Activations