© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136730
    Prev
    Next
    INDEX
    Explanations

    your/my + noun

    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_12_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
    correct
    0.56
     correct
    0.54
     reorgan
    0.54
     सही
    0.53
     corre
    0.52
     hydrological
    0.52
     campi
    0.51
     ସ
    0.49
     он
    0.49
    ﮑ
    0.48
    POSITIVE LOGITS
    يف
    0.54
    手
    0.51
    ஃப்
    0.51
     Estou
    0.51
     руки
    0.50
    bies
    0.50
    ὡ
    0.48
    内外
    0.47
    akia
    0.47
    Hace
    0.47
    Activations Density 0.016%

    No Known Activations