© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47466
    Prev
    Next
    INDEX
    Explanations

    operation silent spring

    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_10_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
    น
    0.80
    of
    0.77
     zakup
    0.65
     precau
    0.62
    l
    0.62
     则
    0.61
    CameraOpened
    0.59
    n
    0.59
    YLE
    0.58
    饮食
    0.58
    POSITIVE LOGITS
     Office
    0.65
     office
    0.55
     EMEA
    0.54
     esimerkiksi
    0.50
    ircon
    0.49
     Managers
    0.49
     Designs
    0.48
     West
    0.48
     Programs
    0.48
     Holistic
    0.48
    Activations Density 0.010%

    No Known Activations