© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35524
    Prev
    Next
    INDEX
    Explanations

    start or begin phrases

    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
    <unused371>
    0.60
    ົວ
    0.59
    -])
    0.57
     வினை
    0.56
    emeni
    0.55
    ēr
    0.54
     ആഘോഷ
    0.54
    <unused413>
    0.54
    䄪
    0.54
    ailability
    0.53
    POSITIVE LOGITS
     {
    0.70
     “
    0.64
     maxim
    0.60
     proteg
    0.57
     sock
    0.57
     server
    0.57
    }
    0.57
     ad
    0.56
     sir
    0.56
    (
    0.55
    Activations Density 0.001%

    No Known Activations