© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48618
    Prev
    Next
    INDEX
    Explanations

    abstract reasoning and distractions

    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_10_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
    c
    0.25
    early
    0.23
    emphas
    0.23
    s
    0.22
    border
    0.21
    bels
    0.21
    expertise
    0.21
     দ্য
    0.21
     on
    0.21
     अंदाज
    0.20
    POSITIVE LOGITS
    :
    0.25
    ONG
    0.21
    reate
    0.20
     natthi
    0.20
     contraste
    0.19
    ON
    0.18
     blackboard
    0.18
     crescimento
    0.18
     desempenho
    0.18
    ONS
    0.18
    Activations Density 0.015%

    No Known Activations