© 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. 207256
    Prev
    Next
    INDEX
    Explanations

    engineering direction

    np_max-act-logits · gemini-2.5-flash-lite
    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
     원
    0.66
    Song
    0.56
     ea
    0.54
     parts
    0.53
     Song
    0.52
     partes
    0.50
    Parts
    0.49
    parts
    0.48
     Teile
    0.47
    With
    0.45
    POSITIVE LOGITS
    heira
    0.43
    blue
    0.43
     arah
    0.42
    笾
    0.41
     engineering
    0.41
     direction
    0.41
     Engineering
    0.40
     방향
    0.40
    ︹
    0.40
    direction
    0.40
    Activations Density 0.001%

    No Known Activations