© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117282
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by opening parenthesis

    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_27_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
    чках
    0.39
    :@
    0.38
    locate
    0.37
    目安
    0.37
    __:
    0.36
    のと
    0.35
    Applicants
    0.34
    历
    0.34
    }]}
    0.33
    IPv
    0.33
    POSITIVE LOGITS
     gouvernement
    0.41
     governo
    0.41
     server
    0.38
     government
    0.37
     govt
    0.37
     لڑکی
    0.35
    衝突
    0.34
     بعد
    0.34
     morally
    0.34
     મહિલા
    0.34
    Activations Density 0.001%

    No Known Activations