© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215039
    Prev
    Next
    INDEX
    Explanations

    land

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
    Wt
    0.41
    rant
    0.40
     Wilk
    0.40
    ЕМ
    0.38
    
    0.37
    carb
    0.37
    뜰
    0.36
    пен
    0.36
     प्रभा
    0.36
    <0xA2>
    0.35
    POSITIVE LOGITS
     journal
    0.42
    WithOwner
    0.41
    owners
    0.40
     sở
    0.40
     OWNER
    0.40
     synchronized
    0.39
     CHAIN
    0.39
    -【
    0.38
     chain
    0.38
     owner
    0.38
    Activations Density 0.001%

    No Known Activations