© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110867
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ن
    0.68
    كو
    0.64
    <unused330>
    0.59
    spiderX
    0.58
    Attk
    0.56
    كيد
    0.55
    𝚙
    0.55
    ك
    0.54
    啼
    0.54
    iodate
    0.54
    POSITIVE LOGITS
    -
    0.71
    u
    0.66
    i
    0.64
    ed
    0.60
     reflecting
    0.59
     on
    0.58
     about
    0.56
    en
    0.55
    es
    0.54
    ef
    0.54
    Activations Density 0.000%

    No Known Activations