© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10843
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to position, arrangement, failure, negativity, or the connection between two things.

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     متعلقه
    -0.70
    WebControls
    -0.58
    }}}}
    -0.53
    Бахар
    -0.52
    XtraGrid
    -0.52
     bezeichneter
    -0.51
     >",
    -0.51
    mær
    -0.51
    ientôt
    -0.50
     ""));
    -0.50
    POSITIVE LOGITS
    Obrázky
    0.58
    Życiorys
    0.54
    osgi
    0.50
    NSData
    0.49
     caminhada
    0.48
    jsonwebtoken
    0.47
    reszcie
    0.47
     dagegen
    0.46
    dfunding
    0.46
     ویکی‌پدیای
    0.46
    Activations Density 17.784%

    No Known Activations