© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210207
    Prev
    Next
    INDEX
    Explanations

    screen size

    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_20_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
    一周
    0.50
    歸
    0.48
    ו
    0.45
    usr
    0.44
     ترک
    0.44
    馨
    0.43
     اجتماعی
    0.42
     तिच्या
    0.41
    ürlich
    0.40
    ើញ
    0.40
    POSITIVE LOGITS
     gazing
    0.51
    ant
    0.47
    ວຍ
    0.46
     pomaga
    0.45
     hlad
    0.44
    Ant
    0.43
    adika
    0.43
    DBG
    0.42
    相同的
    0.42
    𝙳
    0.42
    Activations Density 0.001%

    No Known Activations