© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150890
    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_59_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
    4
    0.47
    Places
    0.46
    8
    0.45
    hand
    0.44
    Adding
    0.42
    9
    0.42
    Hand
    0.41
    Installing
    0.41
    3
    0.41
    list
    0.41
    POSITIVE LOGITS
     RAL
    0.60
     FLE
    0.54
     LEM
    0.53
     RIM
    0.53
     RUD
    0.52
     WORD
    0.51
     Word
    0.51
     SLE
    0.50
     FEL
    0.49
     GLE
    0.49
    Activations Density 0.000%

    No Known Activations