© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30101
    Prev
    Next
    INDEX
    Explanations

    lie or like

    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_10_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
    _
    0.28
    i
    0.28
    for
    0.25
    _|
    0.25
    have
    0.25
    told
    0.24
    ok
    0.24
    s
    0.23
    potato
    0.23
    ने
    0.23
    POSITIVE LOGITS
     v
    0.27
    ра
    0.25
    ци
    0.24
    ться
    0.24
     '
    0.22
    rilor
    0.22
     ше
    0.22
     allong
    0.22
     trừ
    0.22
     দে
    0.22
    Activations Density 0.007%

    No Known Activations