© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2504
    Prev
    Next
    INDEX
    Explanations

    `0x` or `0` followed by hex digits

    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_40_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
     &__
    0.12
     freestyle
    0.11
    值的
    0.11
     сере
    0.11
    隋
    0.11
     Rxb
    0.11
     Biał
    0.11
     mainu
    0.11
     utils
    0.11
    }($
    0.11
    POSITIVE LOGITS
     Farm
    0.13
    oris
    0.12
     Фу
    0.12
     Lom
    0.12
    automated
    0.12
     Autom
    0.12
     Moz
    0.12
    Moz
    0.12
     plan
    0.12
     perf
    0.12
    Activations Density 0.043%

    No Known Activations