© 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. 174076
    Prev
    Next
    INDEX
    Explanations

    Norman Conquest

    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
    hObject
    0.30
    encja
    0.29
    Exe
    0.28
    紹介
    0.27
    QQ
    0.26
    もっと
    0.26
    ující
    0.25
    _
    0.25
    ]->
    0.25
    ्यान
    0.25
    POSITIVE LOGITS
     journaling
    0.31
     katva
    0.31
     Streak
    0.31
     différen
    0.30
    周年
    0.29
     consonant
    0.29
     φυ
    0.29
     Bik
    0.28
    shim
    0.28
     COMPONENTS
    0.28
    Activations Density 0.000%

    No Known Activations