© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213947
    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_50_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
     Mahar
    0.41
    <0xBD>
    0.38
     Ta
    0.38
    wt
    0.38
    ومو
    0.37
    ┣
    0.37
    Robust
    0.36
    Ta
    0.36
    resx
    0.36
    éal
    0.35
    POSITIVE LOGITS
    burgo
    0.44
    nton
    0.41
     maks
    0.39
     spare
    0.39
     ressemble
    0.38
    ungsk
    0.38
     dispar
    0.38
     puer
    0.38
     /ˈ
    0.37
    BCL
    0.37
    Activations Density 0.000%

    No Known Activations