© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14058
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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_13_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
    地说
    0.44
    嵬
    0.44
    rologist
    0.43
     Sulfate
    0.43
    umably
    0.42
    상품
    0.41
    ricamente
    0.41
    ٹھ
    0.41
    機會
    0.41
    tooltip
    0.41
    POSITIVE LOGITS
     взрослых
    0.50
     detract
    0.46
     fabrication
    0.45
     tiredness
    0.45
    _
    0.44
     imping
    0.43
    ین
    0.42
    িম
    0.42
     fabricated
    0.42
     gave
    0.42
    Activations Density 0.030%

    No Known Activations