© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53627
    Prev
    Next
    INDEX
    Explanations

    children danger

    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_30_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
     प्रतियोगी
    0.29
    แนน
    0.27
    बली
    0.27
     COMMIT
    0.27
     определяется
    0.27
     inseparable
    0.26
    决
    0.26
     MEMBERS
    0.26
    エー
    0.26
     committed
    0.25
    POSITIVE LOGITS
     autoclave
    0.34
    ໃຊ້
    0.33
    գ
    0.32
     grazie
    0.28
     prata
    0.28
     hilft
    0.28
     sostit
    0.28
     hospitalization
    0.27
    usega
    0.27
    restrict
    0.27
    Activations Density 0.006%

    No Known Activations