© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 159712
    Prev
    Next
    INDEX
    Explanations

    Warhammer

    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
    :
    1.18
    ných
    1.09
    า
    1.06
    ні
    1.02
    ikten
    1.01
    मधील
    1.01
    nál
    1.01
     dotycz
    0.99
    办法
    0.98
    dings
    0.96
    POSITIVE LOGITS
    ли
    1.41
    し
    1.31
    要
    1.20
    тся
    1.17
    ﺮ
    1.06
    ре
    1.05
    c
    1.05
    g
    1.05
    ции
    1.03
    ﺪ
    1.03
    Activations Density 0.000%

    No Known Activations