© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136609
    Prev
    Next
    INDEX
    Explanations

    challenging environment or task

    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_12_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
    ка
    0.45
    ↵
    0.42
     .
    0.38
    t
    0.37
     preparing
    0.33
     reputations
    0.32
    he
    0.32
    ک
    0.32
    ↵↵
    0.32
     estimates
    0.32
    POSITIVE LOGITS
     भारती
    0.32
     företag
    0.31
    ọi
    0.31
    INIS
    0.31
    <unused39>
    0.31
    ꞎ
    0.31
     föret
    0.30
    önen
    0.30
    ऊंगी
    0.30
     विधेयक
    0.30
    Activations Density 0.002%

    No Known Activations