© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8993
    Prev
    Next
    INDEX
    Explanations

    forts, deserts, salt, and sandstone

    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_13_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
    лог
    0.50
    まったく
    0.48
    論
    0.43
     obi
    0.42
    য়
    0.42
    щі
    0.42
    首都
    0.41
    澈
    0.41
    andte
    0.41
    ਾਈ
    0.41
    POSITIVE LOGITS
    naam
    0.53
     Hota
    0.53
    వారు
    0.53
    na
    0.51
    s
    0.50
     Harv
    0.49
    genius
    0.49
    TAIN
    0.48
    Pada
    0.47
    matu
    0.47
    Activations Density 0.016%

    No Known Activations