© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2732
    Prev
    Next
    INDEX
    Explanations

    line-height CSS property

    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_40_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
    UOUS
    0.41
    卸
    0.37
    sse
    0.37
    𝗇
    0.37
    ธี
    0.36
    哐
    0.36
     стати
    0.35
     døde
    0.35
    ኔታ
    0.35
    亡
    0.35
    POSITIVE LOGITS
     lines
    1.13
     Lines
    0.97
    Lines
    0.92
     líneas
    0.92
     linhas
    0.88
     lignes
    0.84
    lines
    0.81
     line
    0.80
     লাইন
    0.79
     LINES
    0.77
    Activations Density 0.002%

    No Known Activations