© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92833
    Prev
    Next
    INDEX
    Explanations

    URL slugs and identifiers

    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_11_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
    I
    0.23
    :
    0.17
     :
    0.17
    IUS
    0.16
    KI
    0.15
    UM
    0.15
    .:
    0.15
    Prol
    0.15
    IL
    0.14
    But
    0.14
    POSITIVE LOGITS
     Т
    0.17
     కొత్త
    0.16
    ో
    0.16
    president
    0.15
    стью
    0.15
    raient
    0.15
     Э
    0.15
    ்டோ
    0.14
    ad
    0.14
     reorgan
    0.14
    Activations Density 0.004%

    No Known Activations