© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225506
    Prev
    Next
    INDEX
    Explanations

    scenario

    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
     нужно
    0.78
    ވ
    0.78
     تغییر
    0.72
    鉚
    0.72
    ໃຈ
    0.71
    ᱗
    0.71
     варианты
    0.70
    "]
    0.70
     தவிர்க்க
    0.70
     розо
    0.69
    POSITIVE LOGITS
     on
    0.76
    的
    0.72
     e
    0.70
    Http
    0.68
    मा
    0.66
    AT
    0.63
    EN
    0.62
    ED
    0.58
    AD
    0.57
    ੈ
    0.54
    Activations Density 0.024%

    No Known Activations