© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11436
    Prev
    Next
    INDEX
    Explanations

    names of companies or medical products

    oai_token-act-pair · gemini-2.0-flash

    Medical/Tech/Pharma company

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Slf
    -0.59
    beeren
    -0.54
     dobu
    -0.53
    bilisi
    -0.51
    Initializable
    -0.49
    allowNull
    -0.48
    getSimpleName
    -0.47
    atsu
    -0.47
    息
    -0.46
    【
    -0.45
    POSITIVE LOGITS
    AndEndTag
    0.82
    Personensuche
    0.78
     '{@
    0.75
    ergies
    0.71
     beginnetje
    0.65
    expandindo
    0.65
    ]")]
    0.61
    ("]");
    0.60
    MemoryWarning
    0.60
    thâu
    0.59
    Activations Density 0.883%

    No Known Activations