© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12560
    Prev
    Next
    INDEX
    Explanations

    as well, также

    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
    λά
    0.31
    蟳
    0.30
     Bajaj
    0.29
     Saj
    0.29
    ляет
    0.28
     Según
    0.28
    Lbl
    0.28
     ECL
    0.28
     LAD
    0.28
     Héctor
    0.28
    POSITIVE LOGITS
    zing
    0.35
    }.
    0.33
     d
    0.32
    im
    0.32
    pping
    0.32
    !");
    0.32
    !”
    0.32
    w
    0.32
    """
    0.31
    "]
    0.31
    Activations Density 0.006%

    No Known Activations