© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17339
    Prev
    Next
    INDEX
    Explanations

    if

    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_34_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
     Cet
    0.36
    cet
    0.34
    プーン
    0.34
     Gottfried
    0.34
    抂
    0.33
    нь
    0.32
     ordenador
    0.32
    য়োজনীয়
    0.32
    蘄
    0.32
    empire
    0.32
    POSITIVE LOGITS
     if
    1.87
     nếu
    1.66
     если
    1.59
     إذا
    1.57
     jika
    1.53
     dacă
    1.50
     якщо
    1.48
    if
    1.47
     اگر
    1.45
     If
    1.45
    Activations Density 0.194%

    No Known Activations