© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10970
    Prev
    Next
    INDEX
    Explanations

    requires when you working

    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
     tune
    0.51
    tune
    0.48
     diesel
    0.44
    Tune
    0.43
    ティング
    0.42
    ICLE
    0.41
     tunes
    0.41
    ₦
    0.41
     Tune
    0.41
    Systems
    0.40
    POSITIVE LOGITS
    removal
    0.53
     removals
    0.52
     removal
    0.52
     Removal
    0.52
    குழந்த
    0.47
    removing
    0.47
     Remover
    0.46
     desmont
    0.46
     jack
    0.45
     Withdrawal
    0.45
    Activations Density 0.027%

    No Known Activations