© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206502
    Prev
    Next
    INDEX
    Explanations

    apt upgrade system

    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_19_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
    ute
    0.40
    >:
    0.40
    ost
    0.39
    鷲
    0.39
    ended
    0.38
    wic
    0.38
    Fors
    0.38
    apsed
    0.38
    ashed
    0.37
    efeated
    0.37
    POSITIVE LOGITS
     brady
    0.53
     incidencia
    0.48
     일반적으로
    0.46
     জানিতে
    0.46
     mịn
    0.46
     xī
    0.45
    =("
    0.45
     mín
    0.44
     iaa
    0.44
     RUDDER
    0.44
    Activations Density 0.001%

    No Known Activations