© 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. 14437
    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
     നോ
    0.36
     पक
    0.35
     quantifying
    0.35
    াবদ্ধ
    0.35
     quantifier
    0.35
    鳍
    0.35
    Finland
    0.35
    欷
    0.34
     рели
    0.34
     పథ
    0.34
    POSITIVE LOGITS
    ictive
    0.42
     thru
    0.41
    യിലൂടെ
    0.40
    Durch
    0.37
    izoen
    0.36
    ervlak
    0.36
    Localization
    0.36
    ုံး
    0.35
     Puente
    0.35
    بع
    0.35
    Activations Density 0.000%

    No Known Activations