© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161084
    Prev
    Next
    INDEX
    Explanations

    países Bajos

    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_2_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
    a
    2.23
    ي
    1.69
    i
    1.55
    on
    1.54
    x
    1.53
    া
    1.52
    e
    1.52
    p
    1.52
    ne
    1.49
    v
    1.49
    POSITIVE LOGITS
    し
    1.05
    ও
    1.04
    یکس
    0.99
     candidature
    0.97
    னர்
    0.96
    が多く
    0.96
    이었
    0.96
    った
    0.95
    이면
    0.94
    اید
    0.93
    Activations Density 0.000%

    No Known Activations