© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198556
    Prev
    Next
    INDEX
    Explanations

    Question 1 options

    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_9_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
    शंकर
    0.45
    انات
    0.44
     وهي
    0.41
    اسي
    0.41
    pickle
    0.40
    ϛ
    0.40
    零件
    0.39
    trx
    0.39
    pfl
    0.39
    schema
    0.39
    POSITIVE LOGITS
    ی
    0.61
    ad
    0.60
    iv
    0.56
    یا
    0.55
    is
    0.54
    મ
    0.54
    la
    0.52
    ın
    0.52
     fateful
    0.52
    บ
    0.51
    Activations Density 0.000%

    No Known Activations