© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 252807
    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_56_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
    say
    0.63
    Say
    0.59
     —
    0.54
     say
    0.52
     Say
    0.52
     SAY
    0.47
     admit
    0.46
     admits
    0.46
    —
    0.45
     Admit
    0.45
    POSITIVE LOGITS
     complete
    0.48
     Complete
    0.46
     COMPLETE
    0.46
     taking
    0.46
     کامل
    0.44
     presentan
    0.44
     intend
    0.42
    Complete
    0.41
     want
    0.41
     exist
    0.41
    Activations Density 0.000%

    No Known Activations