© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202636
    Prev
    Next
    INDEX
    Explanations

    connection with someone

    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_6_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
    an
    0.80
    t
    0.71
    th
    0.70
    rn
    0.66
    ان
    0.66
    تنا
    0.66
    \
    0.66
    ت
    0.64
    yb
    0.64
    ko
    0.64
    POSITIVE LOGITS
    ना
    0.79
    I
    0.76
    に
    0.72
    에
    0.71
    า
    0.68
    ﺔ
    0.64
    3
    0.61
     년
    0.59
    4
    0.59
     ৪০০
    0.56
    Activations Density 0.001%

    No Known Activations