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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12939
    Prev
    Next
    INDEX
    Explanations

    references to political entities or organizations, especially countries and empires along with related words

    oai_token-act-pair · gemini-2.0-flash

    Roman

    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
    endfor
    -0.48
    htdocs
    -0.46
    []]
    -0.45
    currentTarget
    -0.45
    ❝
    -0.44
    ⓘ
    -0.43
    agna
    -0.43
     Gel
    -0.42
     LoginComponent
    -0.41
    chmal
    -0.41
    POSITIVE LOGITS
    RegistryLite
    0.83
    StoryboardSegue
    0.83
     ISNI
    0.83
     kaarangay
    0.81
     propOrder
    0.79
    GEBURTSDATUM
    0.79
     AssemblyCulture
    0.79
     Roskov
    0.79
     Normdatei
    0.78
    oa̍t
    0.78
    Activations Density 0.220%

    No Known Activations