© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38134
    Prev
    Next
    INDEX
    Explanations

    Apple products and Jobs

    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
    يق
    0.61
    y
    0.60
    ২৮
    0.56
    १०
    0.55
    プロ
    0.54
    يان
    0.54
    Prints
    0.52
    kills
    0.52
    Bitmap
    0.51
    дений
    0.51
    POSITIVE LOGITS
     playlist
    0.64
    </b>
    0.57
     radiological
    0.55
     videos
    0.54
     L
    0.54
     bureaucratic
    0.54
     symptom
    0.53
     orij
    0.53
     cardiac
    0.52
     Vimeo
    0.51
    Activations Density 0.035%

    No Known Activations