© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109558
    Prev
    Next
    INDEX
    Explanations

    Korean, Chinese, Spanish/Portuguese, English language codes

    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_2_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
    お客様
    1.37
    cısı
    1.34
    มี
    1.33
    ル
    1.30
    ित
    1.27
    ある
    1.27
    p
    1.24
    この
    1.21
    daki
    1.19
    มีความ
    1.19
    POSITIVE LOGITS
    ation
    1.15
    P
    1.07
    The
    1.04
     في
    1.02
    Olá
    0.97
    January
    0.96
    August
    0.93
    For
    0.93
    5
    0.93
    Q
    0.93
    Activations Density 0.000%

    No Known Activations