© 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. 28092
    Prev
    Next
    INDEX
    Explanations

    grab a bite

    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
    ют
    0.54
     supposing
    0.53
     doorbell
    0.53
    ítás
    0.53
     עבור
    0.53
     দ্য
    0.52
    т
    0.52
    Y
    0.51
    约定
    0.50
    ت
    0.50
    POSITIVE LOGITS
    bleau
    0.66
     CALIFORNIA
    0.64
    )
    0.64
    ]
    0.61
    riculum
    0.59
    }
    0.59
    olidated
    0.58
     Kõ
    0.58
    to
    0.58
     ITALY
    0.57
    Activations Density 0.022%

    No Known Activations