© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50424
    Prev
    Next
    INDEX
    Explanations

    oceans and water

    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_31_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
    ഹ്ലാ
    0.40
     Hilda
    0.39
     Herod
    0.39
     terrains
    0.38
     Nol
    0.38
     blandit
    0.37
     sporting
    0.37
    阈
    0.36
     diamonds
    0.36
    cX
    0.36
    POSITIVE LOGITS
     Oceans
    0.44
     Venice
    0.43
     Oce
    0.41
    бели
    0.40
    洩
    0.39
     Antim
    0.38
    Ocean
    0.38
     marinas
    0.38
    venth
    0.37
     Venetian
    0.37
    Activations Density 0.008%

    No Known Activations