© 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. 7619
    Prev
    Next
    INDEX
    Explanations

    academic studies and papers

    oai_token-act-pair · gemini-2.0-flash

    academic studies and research-related terms

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

    study

    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
    TagHelper
    -0.53
    ici
    -0.50
    basicConfig
    -0.47
    govina
    -0.46
    #/
    -0.45
    awtextra
    -0.44
    hoeddwyd
    -0.43
    /-/
    -0.43
    ябре
    -0.43
     يتيمه
    -0.42
    POSITIVE LOGITS
     الحره
    0.69
    脚注の使い方
    0.61
    verifyException
    0.58
     addresses
    0.57
     الدولى
    0.54
     CreateTagHelper
    0.54
    RTLR
    0.52
     explored
    0.52
    ?}",
    0.52
     deals
    0.52
    Activations Density 2.409%

    No Known Activations