© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9648
    Prev
    Next
    INDEX
    Explanations

    Sky, BBC, internet

    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_40_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
     synd
    0.44
    ancis
    0.43
     KN
    0.40
     мест
    0.39
    local
    0.38
     syndicate
    0.38
     Synd
    0.37
    侨
    0.35
    acd
    0.35
     ver
    0.35
    POSITIVE LOGITS
     Sky
    0.95
    Sky
    0.91
     sky
    0.79
    SKY
    0.74
    sky
    0.72
     SKY
    0.70
    BBC
    0.59
     BBC
    0.59
     Radio
    0.59
     하늘
    0.57
    Activations Density 0.026%

    No Known Activations