© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13500
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up" and hyphenated words with "up," with a secondary emphasis on the word "down."

    oai_token-act-pair · gemini-2.0-flash

    up

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     up
    -0.59
    帖最后由
    -0.55
    up
    -0.55
    PerformLayout
    -0.54
    hoeddwyd
    -0.54
    upan
    -0.52
    azu
    -0.52
    τας
    -0.51
    Jedis
    -0.51
     détach
    -0.49
    POSITIVE LOGITS
    Scénario
    0.63
    ]:
    0.56
    NewReader
    0.54
    Ranks
    0.52
     AssemblyCulture
    0.51
    RANK
    0.51
    Coming
    0.50
    __(/*!
    0.50
    endphp
    0.50
    createTextNode
    0.50
    Activations Density 1.094%

    No Known Activations