© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11072
    Prev
    Next
    INDEX
    Explanations

    the word "visible" or words with shared roots, regardless of surrounding context

    oai_token-act-pair · gemini-2.0-flash

    visible

    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
    LookAnd
    -1.28
    tagHelperRunner
    -1.15
    ]")]
    -1.10
    hoeddwyd
    -1.07
    principalColumn
    -1.04
    ंदीखरीदारी
    -1.02
    "])
    -1.00
    hyrchwyd
    -0.99
     ویکی‌پدیای
    -0.99
     kaarangay
    -0.95
    POSITIVE LOGITS
    ization
    0.54
    ↵
    0.53
    ↵↵
    0.50
     chao
    0.44
     realiz
    0.43
    ly
    0.43
    了
    0.42
    ists
    0.41
    ting
    0.40
    <strong>
    0.40
    Activations Density 0.693%

    No Known Activations