© 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. 11518
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to financial and government topics such as taxes, budgets, studies, departments, and public announcements

    oai_token-act-pair · gemini-2.0-flash

    Official documents/preparations

    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
     mergeFrom
    -0.53
     snippetHide
    -0.52
    rungsseite
    -0.49
    الحياه
    -0.49
    @[+][
    -0.48
     together
    -0.44
     reh
    -0.44
    באנגלית
    -0.44
     GreatSchools
    -0.44
    ?」
    -0.44
    POSITIVE LOGITS
     HasFactory
    0.57
    mybatisplus
    0.56
     originais
    0.54
    +#+#
    0.53
    esModule
    0.52
     Ebenso
    0.51
     IconData
    0.50
     stimmen
    0.50
     tranquille
    0.50
     totales
    0.49
    Activations Density 9.024%

    No Known Activations