© 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-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10192
    Prev
    Next
    INDEX
    Explanations

    negative political commentary

    oai_token-act-pair · gemini-2.0-flash

    dodge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.93
    BufferException
    -0.86
     EconPapers
    -0.86
     виправивши
    -0.85
     AssemblyTitle
    -0.85
     Paglinawan
    -0.82
    IVEREF
    -0.79
     protoimpl
    -0.76
    IndentedString
    -0.76
    tagHelperRunner
    -0.75
    POSITIVE LOGITS
     dare
    0.45
     adult
    0.44
     tør
    0.44
     daring
    0.42
    optarg
    0.38
     couvert
    0.37
     dared
    0.36
     ahor
    0.36
     Adult
    0.36
     men
    0.36
    Activations Density 0.289%

    No Known Activations