© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97808
    Prev
    Next
    INDEX
    Explanations

    component definition

    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_14_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
     skon
    0.53
    शी
    0.49
    en
    0.48
     triggered
    0.46
    ↵↵
    0.45
    那么
    0.45
    ب
    0.44
    <h3>
    0.44
     बनने
    0.44
    ↵
    0.44
    POSITIVE LOGITS
    StoreException
    0.62
     Jahrhundert
    0.62
    
    0.57
    timevals
    0.56
    ฀
    0.53
    DefinitionGroup
    0.51
     capacitación
    0.51
     crianças
    0.51
    ⧐
    0.51
    navbarSupported
    0.50
    Activations Density 0.000%

    No Known Activations