© 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. 160609
    Prev
    Next
    INDEX
    Explanations

    ตกไหม

    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
    g
    1.45
    w
    1.35
    p
    1.33
    c
    1.28
    ב
    1.25
    ка
    1.21
    ag
    1.18
    ls
    1.16
    j
    1.16
    ,
    1.15
    POSITIVE LOGITS
    이니까
    1.17
     for
    1.11
    見
    1.05
    位置
    1.04
    지
    0.98
    新
    0.97
    ه
    0.96
    Ди
    0.95
    이지만
    0.94
    Но
    0.93
    Activations Density 0.000%

    No Known Activations