© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205509
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    Negative Logits
     thisStudent
    0.48
    𝓎
    0.47
     Wirklich
    0.46
     chủ
    0.45
    ])$.
    0.45
     writers
    0.44
    ちゃう
    0.44
     veröffent
    0.43
     verwenden
    0.43
    ㄏ
    0.43
    POSITIVE LOGITS
    opian
    0.39
     身
    0.39
     opiek
    0.38
    <0xE8>
    0.38
     AppException
    0.37
    乾隆
    0.37
    ক্ট
    0.37
    romo
    0.36
     accrue
    0.36
     σαν
    0.36
    Activations Density 0.000%

    No Known Activations