© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40269
    Prev
    Next
    INDEX
    Explanations

    pay off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    i
    0.70
    ab
    0.64
     definizione
    0.60
    ranging
    0.59
    rem
    0.58
    rare
    0.58
    recognized
    0.58
    as
    0.57
    duration
    0.57
    donation
    0.57
    POSITIVE LOGITS
     เสียง
    0.65
     遅く
    0.65
    MovementControls
    0.64
    SecurityMarks
    0.62
    வாய்
    0.61
     `<=
    0.61
     所以
    0.60
     Elektrokh
    0.60
     บาง
    0.60
     👌
    0.60
    Activations Density 0.001%

    No Known Activations