© 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. 243333
    Prev
    Next
    INDEX
    Explanations

    activate prior knowledge

    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
    Dylan
    0.42
     চল
    0.39
    Las
    0.35
     tally
    0.34
     पाटील
    0.34
    
    0.34
    천
    0.34
    寛
    0.33
    CEA
    0.33
    ㇂
    0.33
    POSITIVE LOGITS
     activate
    1.45
     activation
    1.43
     activating
    1.41
     activations
    1.35
     Activation
    1.34
     activated
    1.32
    激活
    1.31
     activación
    1.31
     Activate
    1.30
    activation
    1.29
    Activations Density 0.005%

    No Known Activations