© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88498
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
     $
    0.63
     channels
    0.63
        
    0.59
    It
    0.55
    <
    0.54
     f
    0.54
    0.52
       
    0.52
     grooves
    0.51
     spots
    0.50
    POSITIVE LOGITS
    ান্ডের
    0.59
     Balliye
    0.57
     BlueprintName
    0.57
    !।
    0.53
    beatCounter
    0.53
     уеннары
    0.53
     TouchUtils
    0.52
    ुल्लाह
    0.52
    ⁈
    0.52
     கெல்வின்
    0.50
    Activations Density 0.000%

    No Known Activations