© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52407
    Prev
    Next
    INDEX
    Explanations

    when `if` `for` `in`

    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_30_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
    inserts
    0.40
    ர்த
    0.35
    那就
    0.35
    但这
    0.34
     collapses
    0.34
     inserts
    0.34
    шек
    0.34
    🦄
    0.34
    insert
    0.33
    Autres
    0.33
    POSITIVE LOGITS
     During
    0.88
     In
    0.76
     When
    0.75
     Within
    0.75
     With
    0.75
     when
    0.74
     Throughout
    0.71
     في
    0.70
     After
    0.69
     Before
    0.68
    Activations Density 0.015%

    No Known Activations