© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 136694
    Prev
    Next
    INDEX
    Explanations

    carved into rock or stone

    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_37_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
     Grass
    0.38
     refl
    0.38
    Grass
    0.38
     dile
    0.38
    flutter
    0.37
    Υ
    0.37
     VD
    0.36
     Brot
    0.36
     $/
    0.36
    Flutter
    0.36
    POSITIVE LOGITS
     carved
    1.06
     rock
    1.00
     carve
    0.91
     cave
    0.91
     carving
    0.88
     caves
    0.84
    Rock
    0.83
    rock
    0.81
     carvings
    0.79
     Rock
    0.78
    Activations Density 0.040%

    No Known Activations