© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180606
    Prev
    Next
    INDEX
    Explanations

    birth control

    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_24_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
     он
    0.40
    菄
    0.40
    しません
    0.39
     剤
    0.38
     weakly
    0.38
    $(\
    0.38
     overjoyed
    0.37
     ($\
    0.37
    rbrakk
    0.37
    みを
    0.37
    POSITIVE LOGITS
     H
    0.43
    的
    0.39
    ↵
    0.38
     Conselho
    0.37
     الكل
    0.36
     सर्वे
    0.36
     Madagascar
    0.35
     নজর
    0.35
     اله
    0.35
     Verify
    0.35
    Activations Density 0.000%

    No Known Activations