© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42067
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases

    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_3_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
    as
    1.00
    T
    0.95
    高
    0.82
    is
    0.80
    ag
    0.79
    os
    0.79
    ak
    0.73
    ad
    0.72
    第二
    0.71
    ul
    0.70
    POSITIVE LOGITS
     WERE
    0.89
     you
    0.81
     \
    0.80
    она
    0.76
     DURING
    0.75
    к
    0.74
     LMFBR
    0.73
     YOU
    0.72
    が大きい
    0.72
    ני
    0.72
    Activations Density 0.005%

    No Known Activations