© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207866
    Prev
    Next
    INDEX
    Explanations

    diverse landscapes

    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_20_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
     компенса
    0.39
    Jackson
    0.38
    収入
    0.37
     Jackson
    0.36
    Stri
    0.35
     recuperación
    0.35
     Gustavo
    0.35
    ⠈
    0.35
    Bob
    0.34
    Ash
    0.34
    POSITIVE LOGITS
    announced
    0.40
     Bereiche
    0.40
     which
    0.38
     vilket
    0.38
     Which
    0.37
     varied
    0.37
     announces
    0.37
     ended
    0.37
     beet
    0.37
     whiche
    0.37
    Activations Density 0.006%

    No Known Activations