© 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
    2. Gemma-3-27B-IT
    3. 44-GEMMASCOPE-2-TRANSCODER-262K
    4. 103514
    Prev
    Next
    INDEX
    Explanations

    math expressions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ")[
    0.72
    )²
    0.68
    }})^{
    0.68
    ')[
    0.66
    )^
    0.66
    })^{
    0.65
    )^{
    0.64
    )[
    0.64
    ]^{
    0.64
    )^(
    0.63
    POSITIVE LOGITS
     চলতে
    0.38
     그러면은
    0.37
     वाट
    0.36
     बिन
    0.36
     मिलेगी
    0.36
     विराज
    0.35
    রাজ
    0.35
     могли
    0.35
     willpower
    0.35
     नाच
    0.35
    Activations Density 0.003%

    No Known Activations