© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7920
    Prev
    Next
    INDEX
    Explanations

    words related to programming or foreign languages

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    "):
    -0.69
     non
    -0.68
    titious
    -0.66
    neous
    -0.66
    }>;
    -0.65
    ANEOUS
    -0.65
    로운
    -0.64
    PyExc
    -0.63
     pure
    -0.63
    iguous
    -0.63
    POSITIVE LOGITS
    <bos>
    0.88
    AndEndTag
    0.71
     bénévoles
    0.69
     genoux
    0.68
     infallib
    0.68
     toppen
    0.66
     réfugiés
    0.65
     rangement
    0.64
     témoins
    0.64
     blessés
    0.63
    Activations Density 0.420%

    No Known Activations