© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11794
    Prev
    Next
    INDEX
    Explanations

    women's rights and disadvantages

    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_13_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
     제거
    0.48
     आवासीय
    0.44
     PWMB
    0.44
    л
    0.42
     Cahill
    0.42
    astico
    0.42
    iffen
    0.42
     منظر
    0.41
    vacuum
    0.40
     بیان
    0.40
    POSITIVE LOGITS
    üss
    0.44
     svjets
    0.43
    uscular
    0.40
     number
    0.39
    გი
    0.39
    PO
    0.38
     ذوالفقار
    0.38
    }'],
    0.37
    ev
    0.37
     број
    0.37
    Activations Density 0.019%

    No Known Activations