© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12695
    Prev
    Next
    INDEX
    Explanations

    higher, easier, late, difficult, harder

    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_40_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
     emphasised
    0.41
    ায়ক
    0.39
     unbeatable
    0.38
    busch
    0.37
     Organisation
    0.36
    seamless
    0.36
     molto
    0.36
    🛡
    0.35
     होंगी
    0.35
     πολύ
    0.35
    POSITIVE LOGITS
     Among
    0.48
    Among
    0.42
     among
    0.40
     среди
    0.39
     Decl
    0.37
     Среди
    0.37
    */)
    0.36
     wśród
    0.36
    ОВА
    0.36
    ността
    0.35
    Activations Density 0.026%

    No Known Activations