© 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. 13919
    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
     units
    0.39
     Hardly
    0.37
     TER
    0.37
     unit
    0.36
    Units
    0.36
    倶
    0.36
     Act
    0.35
    unit
    0.35
    分支
    0.35
    TAR
    0.35
    POSITIVE LOGITS
    ក
    0.40
     victoria
    0.38
     concentração
    0.38
     deutscher
    0.37
    ဗ
    0.36
     maaf
    0.35
     ဗ
    0.35
    ⁶
    0.35
    issants
    0.34
     integrar
    0.34
    Activations Density 0.000%

    No Known Activations