© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7399
    Prev
    Next
    INDEX
    Explanations

    names of people reading research papers

    oai_token-act-pair · gemini-2.0-flash

    researchers' names and affiliations

    np_token-act-pair-logits · gpt-4o-mini

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    帖最后由
    -0.65
     getWidth
    -0.60
     nameof
    -0.52
    Slf
    -0.51
     stöd
    -0.50
     llorar
    -0.50
     @"/
    -0.49
     Wikimedijinoj
    -0.49
     getHeight
    -0.49
    figcaption
    -0.49
    POSITIVE LOGITS
    RPD
    0.49
    bha
    0.48
     Cohen
    0.45
    ofold
    0.44
    hai
    0.44
    ἶ
    0.43
    mbler
    0.43
    bella
    0.43
    hlás
    0.42
    paganda
    0.42
    Activations Density 1.886%

    No Known Activations