© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5073
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with advertising, especially for free services or products

    oai_token-act-pair · gemini-2.0-flash

    online marketing ads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tvguidetime
    -0.55
     Chwiliwch
    -0.53
    Hentet
    -0.53
    Hochspringen
    -0.51
    UnsafeEnabled
    -0.49
    RetentionPolicy
    -0.48
    PathParam
    -0.44
    forChild
    -0.44
    ScopeManager
    -0.43
     CreateTagHelper
    -0.43
    POSITIVE LOGITS
    Купить
    0.58
     Vote
    0.57
    )';
    0.57
    ··
    0.57
     Api
    0.57
    قایناق‌لار
    0.57
    %?
    0.56
    "%(
    0.56
    FundMe
    0.55
     noqa
    0.54
    Activations Density 26.767%

    No Known Activations