© 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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1451
    Prev
    Next
    INDEX
    Explanations

    political commentary, especially regarding racism, social issues, and government

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.58
     happy
    -0.52
     Perry
    -0.50
     inoc
    -0.49
     PERRY
    -0.46
    inium
    -0.45
    })+\
    -0.45
    ónimo
    -0.45
     ménages
    -0.44
    <eos>
    -0.43
    POSITIVE LOGITS
    StructEnd
    0.74
    はじめに
    0.66
     >=",
    0.66
     صوتيه
    0.64
     الرياضيه
    0.63
     poffible
    0.63
     correctes
    0.61
    رشف
    0.59
    webElementXpaths
    0.56
    település
    0.56
    Activations Density 5.595%

    No Known Activations