© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235348
    Prev
    Next
    INDEX
    Explanations

    physical stores

    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_46_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
     brick
    3.48
    Brick
    3.14
     bricks
    3.11
     Brick
    3.05
    brick
    3.02
    bricks
    2.66
    砖
    2.44
     кирпи
    2.42
    磚
    2.25
     ladr
    1.45
    POSITIVE LOGITS
     표
    0.38
    nesium
    0.37
    孃
    0.37
     plur
    0.37
     cerebellum
    0.36
     dél
    0.36
     டன்
    0.35
    ग्रस्त
    0.35
     blanch
    0.34
    ícula
    0.34
    Activations Density 0.009%

    No Known Activations