© 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. 4737
    Prev
    Next
    INDEX
    Explanations

    historical/cultural descriptors followed by related concepts

    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
    ванні
    0.35
     perpetuated
    0.33
    សម្
    0.33
     Smartphones
    0.33
     Appliances
    0.33
    掫
    0.33
     flame
    0.32
    änn
    0.32
     simultaneously
    0.32
     cig
    0.32
    POSITIVE LOGITS
    hitth
    0.38
    absValue
    0.37
    腋
    0.36
     FV
    0.35
    kala
    0.34
     Regime
    0.34
     INSPE
    0.34
    awks
    0.34
    ITY
    0.33
    argy
    0.33
    Activations Density 0.068%

    No Known Activations