© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78635
    Prev
    Next
    INDEX
    Explanations

    water followed by various contexts

    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_0_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
    y
    2.67
    d
    2.23
    n
    2.05
    r
    1.84
    l
    1.84
    j
    1.71
    h
    1.70
    q
    1.68
    ll
    1.65
    a
    1.64
    POSITIVE LOGITS
    ח
    1.77
    ک
    1.60
    기
    1.51
    ك
    1.48
    یل
    1.46
    л
    1.46
     ένα
    1.45
    ш
    1.45
    ל
    1.42
     время
    1.39
    Activations Density 0.000%

    No Known Activations