© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14799
    Prev
    Next
    INDEX
    Explanations

    phone number

    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_40_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
    㑼
    0.37
    oxyl
    0.37
    𝐰
    0.35
     क्वाड्र
    0.34
     گردد
    0.34
    здат
    0.33
    ヅ
    0.33
     উদ্বাস্তু
    0.33
    ᄐ
    0.33
    𒀉
    0.33
    POSITIVE LOGITS
     cellphone
    1.98
    手机
    1.92
     mobile
    1.85
    手機
    1.77
     मोबाइल
    1.71
     মোবাইল
    1.68
     phone
    1.67
    携帯
    1.66
     cell
    1.62
     Mobile
    1.59
    Activations Density 0.058%

    No Known Activations