© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76312
    Prev
    Next
    INDEX
    Explanations

    audience and context questions

    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
     seats
    0.46
    Seats
    0.44
     kursi
    0.42
     avven
    0.41
     anywhere
    0.40
    বার্গ
    0.40
     சென்னை
    0.40
    칵
    0.40
     seated
    0.39
    orkeling
    0.38
    POSITIVE LOGITS
     manager
    0.43
     Managers
    0.41
     managers
    0.41
     менедже
    0.41
     consumers
    0.38
     insiders
    0.38
     jitter
    0.37
     readers
    0.37
     inspectors
    0.37
    itory
    0.36
    Activations Density 0.011%

    No Known Activations