© 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. 75447
    Prev
    Next
    INDEX
    Explanations

    circuit, controller, holder, or belt accessories

    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
     corrupt
    0.27
    कहां
    0.27
    បង្
    0.26
    醝
    0.26
    θεση
    0.26
     gul
    0.26
     stronghold
    0.25
     með
    0.25
    Counsel
    0.25
     голе
    0.25
    POSITIVE LOGITS
     ಅಥವಾ
    0.29
     photospheric
    0.27
     radiographic
    0.26
     अथवा
    0.26
    switchTo
    0.26
    }^{*}
    0.26
     cinta
    0.26
     фотографи
    0.26
    leaflet
    0.26
     depictions
    0.25
    Activations Density 0.004%

    No Known Activations