© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198472
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific discoveries

    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_15_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
     having
    0.54
     आणि
    0.53
     impair
    0.53
     $[\
    0.53
     toplant
    0.53
     마음
    0.52
    सभा
    0.51
     Mub
    0.51
     falling
    0.50
     करण्या
    0.50
    POSITIVE LOGITS
    äns
    0.50
    Fees
    0.46
    ूली
    0.46
    ätt
    0.45
    ä
    0.44
     buffers
    0.43
    ponds
    0.42
    Jobs
    0.42
    U
    0.42
     hassles
    0.41
    Activations Density 0.000%

    No Known Activations