© 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. 10023
    Prev
    Next
    INDEX
    Explanations

    phrases related to remembering, considering, and keeping things in mind

    oai_token-act-pair · gemini-2.0-flash

    mind

    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
    bootstrapcdn
    -0.66
     Réponses
    -0.63
     ویکی‌پدی
    -0.63
    Tazama
    -0.60
     programmet
    -0.59
    Program
    -0.57
     Programm
    -0.57
     nôtre
    -0.57
     للاسماء
    -0.55
     prêts
    -0.54
    POSITIVE LOGITS
    スメ
    0.58
    ENE
    0.51
    writerow
    0.50
     temper
    0.50
    mybatisplus
    0.49
     كومونز
    0.48
    scriptcase
    0.48
     temp
    0.47
    MergeFrom
    0.46
    <tfoot>
    0.46
    Activations Density 0.762%

    No Known Activations