© 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. 12259
    Prev
    Next
    INDEX
    Explanations

    URLs and book reviews

    oai_token-act-pair · gemini-2.0-flash

    watch or reading

    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
    сылкі
    -0.68
    StoryboardSegue
    -0.64
     bezeichneter
    -0.60
     Direito
    -0.60
    <bos>
    -0.60
    KommentareTeilen
    -0.58
     дописавши
    -0.57
     automatiques
    -0.57
     commerciales
    -0.55
     individuelles
    -0.55
    POSITIVE LOGITS
     հղումներ
    0.56
     Réponses
    0.53
    RunWith
    0.49
    choon
    0.48
    setColumns
    0.46
    scryfall
    0.46
    CopyWith
    0.45
    //
    0.42
    فيات
    0.42
    onAttach
    0.42
    Activations Density 0.802%

    No Known Activations