© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33916
    Prev
    Next
    INDEX
    Explanations

    say "B" words

    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_50_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
    namespaces
    0.37
    composable
    0.35
    涫
    0.35
     decompositions
    0.34
    記念
    0.34
     Razer
    0.34
    荘
    0.34
     munch
    0.33
    thickmathspace
    0.33
    🤽
    0.33
    POSITIVE LOGITS
     brothers
    2.44
     Brother
    2.38
     Brothers
    2.34
     brother
    2.33
    Brother
    2.31
    brothers
    2.23
    brother
    2.17
    兄弟
    2.13
     брат
    1.98
     irmãos
    1.95
    Activations Density 0.000%

    No Known Activations