© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101633
    Prev
    Next
    INDEX
    Explanations

    instructions with "should not"

    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_16_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
    uszcz
    0.54
    west
    0.52
    ﮈ
    0.50
     ее
    0.50
     gravité
    0.50
    we
    0.49
    was
    0.47
    ුවේ
    0.47
    ub
    0.47
    ubro
    0.47
    POSITIVE LOGITS
     howling
    0.46
     Möbius
    0.46
     reg
    0.45
    f
    0.45
    ก
    0.45
     inhibitors
    0.45
     ganze
    0.45
     transistors
    0.44
    নাম
    0.43
     knockout
    0.43
    Activations Density 0.000%

    No Known Activations