© 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. 13877
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and notation

    oai_token-act-pair · gemini-2.0-flash

    phrases introducing definitions or explanations

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

    we

    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
    enschappelijke
    -0.62
    Hochspringen
    -0.58
    Чыганаклар
    -0.57
    yntaxException
    -0.56
     SwitchCompat
    -0.56
    findpost
    -0.52
    medriver
    -0.52
    ronique
    -0.52
    mocks
    -0.52
    onn
    -0.52
    POSITIVE LOGITS
     let
    0.85
     set
    0.75
     setting
    0.71
    令
    0.70
     letting
    0.69
     Set
    0.64
     define
    0.62
     Let
    0.61
    setting
    0.60
     Setting
    0.59
    Activations Density 4.798%

    No Known Activations