© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217471
    Prev
    Next
    INDEX
    Explanations

    FBI

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     وغير
    0.41
     AUDIO
    0.39
     అయ్య
    0.39
     ভর্ত
    0.38
    sthresh
    0.38
    捃
    0.38
    んです
    0.38
     Vo
    0.37
    ೊಳ್ಳ
    0.37
     ዓ
    0.37
    POSITIVE LOGITS
     Rfc
    0.44
    Eth
    0.39
     prognostic
    0.38
    ூர்
    0.38
    oct
    0.38
     hideous
    0.37
    vious
    0.37
     horribly
    0.37
    écie
    0.37
    agian
    0.36
    Activations Density 0.001%

    No Known Activations