© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13389
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word 'add' and/or the preposition 'with'

    oai_token-act-pair · gemini-2.0-flash

    words related to adding or increasing

    np_token-act-pair-logits · gpt-4o-mini

    add

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    writeFieldEnd
    -0.76
    Personendaten
    -0.66
     الرياضيه
    -0.61
    BagLayout
    -0.56
     refroid
    -0.53
     endwhile
    -0.52
    saraba
    -0.52
    Xna
    -0.51
    PhysRev
    -0.50
    readFileSync
    -0.50
    POSITIVE LOGITS
    SpringBootTest
    0.90
     to
    0.68
    /*
    0.54
    Privilege
    0.53
    mybatisplus
    0.52
    ///</
    0.51
     Benav
    0.50
    (!__
    0.50
    出版年
    0.50
    rapeau
    0.49
    Activations Density 9.743%

    No Known Activations