© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137057
    Prev
    Next
    INDEX
    Explanations

    pi electrons in conjugated systems

    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_12_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
    v
    0.27
    OUR
    0.26
    ！
    0.26
    ANS
    0.25
    ands
    0.25
    OUT
    0.25
    t
    0.25
    СТ
    0.24
    "
    0.24
    高峰
    0.24
    POSITIVE LOGITS
    டைந்த
    0.23
    cheiden
    0.22
    eiro
    0.22
     seigneur
    0.22
     `{
    0.21
     scathing
    0.21
     fainting
    0.21
     bravely
    0.21
     McPherson
    0.20
     `<=
    0.20
    Activations Density 0.001%

    No Known Activations