© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11639
    Prev
    Next
    INDEX
    Explanations

    clauses starting with "if you"

    oai_token-act-pair · gemini-2.0-flash

    user intention or plans

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

    you

    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
     snippetHide
    -0.75
    fromnode
    -0.52
    BagConstraints
    -0.51
     inappropriés
    -0.51
    BeginContext
    -0.50
     Biôgrafia
    -0.50
    campista
    -0.50
    newcommand
    -0.49
    tiously
    -0.49
     كومونز
    -0.48
    POSITIVE LOGITS
     plan
    0.66
     intend
    0.66
     intention
    0.61
     find
    0.60
     wanted
    0.60
     want
    0.59
    +#+
    0.58
     surla
    0.57
    BuildContext
    0.56
    findUser
    0.56
    Activations Density 1.889%

    No Known Activations