© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195799
    Prev
    Next
    INDEX
    Explanations

    global and internationally recognized

    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_15_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
    Corruption
    0.25
    _{
    0.22
    ]?
    0.21
    ाम
    0.21
    θν
    0.20
    corruption
    0.20
    ون
    0.20
    meeting
    0.20
    凖
    0.20
    ประเทศ
    0.20
    POSITIVE LOGITS
     erforderlich
    0.25
     Spieler
    0.23
    endir
    0.23
     Darrell
    0.23
     toured
    0.23
    inoceros
    0.22
     caminar
    0.22
     parámetro
    0.22
     Rider
    0.22
    ચર
    0.22
    Activations Density 0.003%

    No Known Activations