© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178226
    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_29_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
     soft
    0.34
     kendi
    0.34
    Pile
    0.34
     pile
    0.33
    ぅ
    0.32
     அறு
    0.31
     flavors
    0.31
     kuid
    0.31
    从此
    0.31
     individ
    0.31
    POSITIVE LOGITS
     DISEASE
    0.37
     Recipients
    0.36
     завое
    0.35
     noreferrer
    0.35
     bridesmaid
    0.34
    ंजन
    0.33
     disdain
    0.33
     pandemic
    0.33
    🐭
    0.33
     शिल्पा
    0.33
    Activations Density 0.000%

    No Known Activations