© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14808
    Prev
    Next
    INDEX
    Explanations

    physics and mathematics academic journal titles or related terms in citations

    oai_token-act-pair · gemini-2.0-flash

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.52
    ')):
    -0.48
     himo
    -0.47
    lovakia
    -0.46
    )))))
    -0.44
    ))/
    -0.41
     أعلام
    -0.41
    figs
    -0.41
     devaient
    -0.41
    øren
    -0.40
    POSITIVE LOGITS
     propOrder
    0.70
    Portail
    0.69
    endphp
    0.59
    Hozzáférés
    0.57
     GenerationType
    0.57
    Composable
    0.57
     &___
    0.57
    BagConstraints
    0.57
    __*/
    0.56
     onOptions
    0.56
    Activations Density 0.360%

    No Known Activations