© 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. 29828
    Prev
    Next
    INDEX
    Explanations

    inputs and outputs

    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
     cartridges
    0.45
     cartilage
    0.44
    カートリッジ
    0.44
     cartridge
    0.42
    duck
    0.41
    လ
    0.41
     cornea
    0.39
    दर्शी
    0.38
    leece
    0.38
    鴨
    0.38
    POSITIVE LOGITS
     Input
    0.46
    Input
    0.45
    Rez
    0.45
     input
    0.45
     Inputs
    0.45
    input
    0.43
    Outputs
    0.43
     inputs
    0.42
     intakes
    0.41
     inlet
    0.39
    Activations Density 0.045%

    No Known Activations