© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152869
    Prev
    Next
    INDEX
    Explanations

    arrests, imprisonment

    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_23_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
    掍
    0.46
    掑
    0.44
    शिष्ट
    0.41
    شور
    0.40
    hésitez
    0.38
    parametri
    0.38
    估计
    0.38
    плення
    0.38
    𝙄
    0.38
     الشعر
    0.38
    POSITIVE LOGITS
     بو
    0.42
    urations
    0.39
     sól
    0.39
     debunk
    0.38
     dû
    0.37
    🏚
    0.37
     underpinned
    0.37
     Palash
    0.37
     repress
    0.37
     المسي
    0.37
    Activations Density 0.002%

    No Known Activations