© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    sentences which introduce the existence of something

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "there"

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

    there

    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
    LEncoder
    -0.59
    elemField
    -0.57
    numerusform
    -0.53
    toggler
    -0.52
    INCREF
    -0.52
    |}{$
    -0.52
     يتيمه
    -0.51
    roupa
    -0.49
     ongles
    -0.49
    IndentedString
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.56
     itself
    0.53
     wireType
    0.52
    moveToFirst
    0.49
     Sollte
    0.48
     laying
    0.47
    lapsingToolbar
    0.46
    onema
    0.46
     Öster
    0.46
    ArrowToggle
    0.46
    Activations Density 0.416%

    No Known Activations