© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26007
    Prev
    Next
    INDEX
    Explanations

    protocol, phosphate, provider

    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_10_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
    as
    1.27
    त
    1.10
    い
    1.08
    는
    1.02
    up
    0.99
    含ま
    0.98
    ول
    0.96
    h
    0.96
    be
    0.93
    ла
    0.93
    POSITIVE LOGITS
    大
    1.00
    ד
    0.99
    이었다
    0.93
    原因
    0.93
    心
    0.89
    ,
    0.86
    ית
    0.85
    ни
    0.82
     gratu
    0.81
     to
    0.81
    Activations Density 0.098%

    No Known Activations