© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131007
    Prev
    Next
    INDEX
    Explanations

    over [time/years/centuries/millennia]

    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_1_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
    ar
    1.22
    ina
    1.20
    ers
    1.13
    ast
    1.10
    ap
    1.09
    ana
    1.08
    8
    1.06
    ill
    1.05
    arie
    1.05
    7
    1.05
    POSITIVE LOGITS
    した
    1.37
    め
    1.16
    کی
    1.15
    も
    1.12
    کن
    1.08
    gheatmap
    1.08
    をした
    1.07
    をして
    1.06
    первых
    1.05
    引き
    1.05
    Activations Density 0.005%

    No Known Activations