© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61387
    Prev
    Next
    INDEX
    Explanations

    vessel

    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_11_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
    ul
    0.76
    بي
    0.72
    infection
    0.71
    ке
    0.69
    고
    0.69
    utilisation
    0.68
    プ
    0.68
    كلم
    0.65
    سك
    0.65
    ба
    0.65
    POSITIVE LOGITS
     an
    0.73
     il
    0.73
     यहां
    0.70
     Ι
    0.70
     Mia
    0.70
     point
    0.69
     de
    0.66
     ind
    0.66
     ai
    0.66
     MIA
    0.66
    Activations Density 0.002%

    No Known Activations