© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125235
    Prev
    Next
    INDEX
    Explanations

    source code or server

    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_3_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
    un
    1.00
    for
    0.90
    e
    0.78
    she
    0.76
    j
    0.76
    ib
    0.75
    an
    0.73
    sm
    0.73
    smith
    0.71
    sal
    0.70
    POSITIVE LOGITS
     slices
    0.77
    ב
    0.74
     blooms
    0.73
     strides
    0.72
     blasts
    0.71
     pivots
    0.71
     bursts
    0.71
     м
    0.71
     aches
    0.70
     rains
    0.70
    Activations Density 0.002%

    No Known Activations