© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246421
    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_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
     පැ
    0.42
     hardwoods
    0.37
     premise
    0.37
     varnish
    0.37
     άλ
    0.37
    ,}$
    0.37
     rising
    0.36
    جلد
    0.36
    遗传
    0.35
    CONFIGURATION
    0.35
    POSITIVE LOGITS
    javase
    0.42
    業
    0.40
     cual
    0.38
     AMR
    0.37
     Elevator
    0.37
     absorber
    0.36
    MenuActive
    0.36
     участия
    0.35
     thấp
    0.35
    centerY
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.