© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168309
    Prev
    Next
    INDEX
    Explanations

    keeping

    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
    ').':
    0.41
     மத்திய
    0.38
    tween
    0.37
     certa
    0.36
    rolysis
    0.36
     Attic
    0.36
     complete
    0.35
     $:=$
    0.35
     hela
    0.35
    hooting
    0.35
    POSITIVE LOGITS
     track
    1.02
    track
    0.89
    Track
    0.85
     Track
    0.77
     ट्रैक
    0.73
     tracks
    0.68
    TRACK
    0.59
     TRACK
    0.58
    トラック
    0.57
     ট্র্যাক
    0.55
    Activations Density 0.002%

    No Known Activations