© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143592
    Prev
    Next
    INDEX
    Explanations

    attract and draw attention

    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_0_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
    g
    1.95
    k
    1.90
    ia
    1.78
    ek
    1.74
    s
    1.72
    ing
    1.64
    a
    1.62
    d
    1.61
    ev
    1.57
    p
    1.54
    POSITIVE LOGITS
    ਰ
    1.66
    つ
    1.36
    4
    1.32
    }.
    1.29
    {
    1.25
    ++;
    1.19
    য়া
    1.16
    )?;
    1.16
    اری
    1.15
     gái
    1.15
    Activations Density 0.000%

    No Known Activations