© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 449
    Prev
    Next
    INDEX
    Explanations

    mostly Danish words and phrases, particularly titles of movies that contain release years in parentheses.

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     an
    -0.43
    H
    -0.40
     myel
    -0.40
    unie
    -0.39
    spender
    -0.39
     Presbyter
    -0.39
    OP
    -0.38
    databinding
    -0.38
    obenz
    -0.36
     anh
    -0.36
    POSITIVE LOGITS
     '\\;'
    0.88
    NameInMap
    0.85
    Autoritní
    0.84
    IsContent
    0.79
     betweenstory
    0.77
     lenker
    0.76
    RegressionTest
    0.75
    følgelig
    0.75
    SourceChecksum
    0.75
    aarrggbb
    0.74
    Activations Density 0.821%

    No Known Activations