© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154151
    Prev
    Next
    INDEX
    Explanations

    say "water" words

    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_60_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
     water
    0.78
     Water
    0.76
     WATER
    0.74
     acqua
    0.69
     水
    0.63
     nước
    0.60
     agua
    0.60
     watermark
    0.60
     वाटर
    0.58
    の水
    0.57
    POSITIVE LOGITS
    cool
    0.71
    some
    0.68
    Some
    0.59
    still
    0.58
    quick
    0.55
     einigen
    0.54
    一些
    0.53
    near
    0.51
     einige
    0.50
    冰
    0.50
    Activations Density 0.002%

    No Known Activations