© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2981
    Prev
    Next
    INDEX
    Explanations

    references to people, situations, and circumstances

    oai_token-act-pair · gemini-2.0-flash

    foreign or non-English language elements

    np_token-act-pair-logits · gpt-4o-mini
    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
     he
    -1.91
    He
    -1.59
     он
    -1.51
     him
    -1.47
     He
    -1.41
    彼は
    -1.29
    他
    -1.27
     他
    -1.21
    he
    -1.20
    Он
    -1.18
    POSITIVE LOGITS
    AndEndTag
    0.99
     فريبيس
    0.88
     @"/
    0.87
     Normdatei
    0.84
     Roskov
    0.75
    StoryboardSegue
    0.75
    ثيق
    0.74
     kaarangay
    0.73
     autorytatywna
    0.73
    ChildScrollView
    0.73
    Activations Density 8.864%

    No Known Activations