© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12925
    Prev
    Next
    INDEX
    Explanations

    a range of words associated with different contexts, including proximity/confrontation (e.g., "face to face"), legal disputes (e.g., "contends"), news/media (e.g., "news", "Morning"), and scientific terms (e.g., "dise

    oai_token-act-pair · gemini-2.0-flash

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    esModule
    -0.69
    bufio
    -0.63
     sponsors
    -0.59
    propTypes
    -0.58
     UnityEditor
    -0.55
    Sponsor
    -0.52
    Sponsors
    -0.52
    esten
    -0.52
     sponsor
    -0.52
    principalTable
    -0.50
    POSITIVE LOGITS
     with
    1.13
    with
    0.80
     avec
    0.79
     dengan
    0.76
    With
    0.70
    tagext
    0.70
     WITH
    0.69
     With
    0.66
    zarchiwizowane
    0.64
    avec
    0.63
    Activations Density 6.223%

    No Known Activations