© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165437
    Prev
    Next
    INDEX
    Explanations

    postdoctoral roles and researcher positions

    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_13_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
     искусство
    0.59
     энергия
    0.58
    ⊱
    0.58
     Daw
    0.57
    格子
    0.55
     энергии
    0.55
     KFC
    0.55
     Saw
    0.54
     రోజు
    0.54
     employé
    0.54
    POSITIVE LOGITS
    And
    0.64
    us
    0.61
    :
    0.59
    &
    0.57
    There
    0.55
     and
    0.55
    <b>
    0.54
    a
    0.53
    Α
    0.53
    <strong>
    0.52
    Activations Density 0.000%

    No Known Activations