© 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. 177203
    Prev
    Next
    INDEX
    Explanations

    session, command, list, scanner, player

    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
     Mahi
    0.18
    电设备
    0.17
     mahi
    0.17
    든
    0.17
    ジン
    0.16
    otesi
    0.16
     радиа
    0.16
     অধ্যয়ন
    0.16
    SRP
    0.15
    getExternal
    0.15
    POSITIVE LOGITS
    ჩ
    0.21
     puzzling
    0.21
     surprising
    0.20
     natürlich
    0.20
     unusual
    0.19
     paw
    0.19
     contradictory
    0.19
     baffling
    0.19
     jok
    0.19
     waarbij
    0.18
    Activations Density 0.003%

    No Known Activations