© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195750
    Prev
    Next
    INDEX
    Explanations

    water

    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_50_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
     hole
    0.80
     Hole
    0.79
    hole
    0.77
    holes
    0.67
     holes
    0.61
     होल
    0.61
     Holes
    0.61
    穴
    0.51
    Hol
    0.49
     Hol
    0.48
    POSITIVE LOGITS
    леп
    0.41
     syair
    0.40
    ღვ
    0.40
    kati
    0.37
     Lenn
    0.37
    lexeme
    0.37
     জাতিসঙ্ঘ
    0.37
     busses
    0.36
     உண்டு
    0.36
    пус
    0.36
    Activations Density 0.002%

    No Known Activations