© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202912
    Prev
    Next
    INDEX
    Explanations

    something is necessary

    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_6_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
    ك
    1.07
    ד
    0.91
    را
    0.90
    ח
    0.89
    ו
    0.87
     an
    0.86
     for
    0.80
    د
    0.80
    ล
    0.80
    UR
    0.79
    POSITIVE LOGITS
    ların
    0.84
     години
    0.81
     cordial
    0.80
     생각
    0.78
     qualità
    0.77
     уровень
    0.77
    imientos
    0.76
     були
    0.75
    ᱼ
    0.75
     সিদ্ধান্ত
    0.75
    Activations Density 0.001%

    No Known Activations