© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44258
    Prev
    Next
    INDEX
    Explanations

    demand for harmful content

    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_22_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
    iziModal
    0.36
    Comfort
    0.33
    ໃຈ
    0.33
    Dn
    0.32
    
    0.32
    Brooklyn
    0.32
    েন্দ্রলাল
    0.31
    ubble
    0.30
    ycop
    0.30
     අධ
    0.30
    POSITIVE LOGITS
     Tar
    0.33
     sano
    0.31
    す
    0.31
    так
    0.30
    āo
    0.30
     Pat
    0.30
     gab
    0.30
    ệ
    0.29
     punishment
    0.29
     Wah
    0.29
    Activations Density 0.024%

    No Known Activations