© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177510
    Prev
    Next
    INDEX
    Explanations

    '@Entity' or '@Mapper' class definitions

    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_24_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
     heo
    0.39
     હો
    0.38
    UTH
    0.38
     English
    0.37
     Akan
    0.37
     merid
    0.36
    ☜
    0.36
    ราะ
    0.36
     mencegah
    0.36
    రికి
    0.36
    POSITIVE LOGITS
    蝰
    0.42
    Paxos
    0.41
    ıs
    0.41
     کسب
    0.40
    规范
    0.37
    业务
    0.37
    ައ
    0.36
    viridis
    0.36
     Kaltura
    0.36
    Benzyl
    0.36
    Activations Density 0.000%

    No Known Activations