© 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. 17603
    Prev
    Next
    INDEX
    Explanations

    turbocharged / non-turbo engine systems

    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
    排名
    0.43
     RANK
    0.41
     អ្នក
    0.41
    해야
    0.39
    ᡳ
    0.39
     ranking
    0.38
    rank
    0.38
     peringkat
    0.38
    Rank
    0.38
     rankings
    0.38
    POSITIVE LOGITS
     inlet
    0.44
    窒
    0.41
     maximization
    0.41
     Optimization
    0.40
     Charging
    0.39
     напол
    0.39
     Filed
    0.38
     memak
    0.38
    嗪
    0.38
     Inlet
    0.38
    Activations Density 0.017%

    No Known Activations