© 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. 6407
    Prev
    Next
    INDEX
    Explanations

    references to consuming food in food reviews

    oai_token-act-pair · gemini-2.0-flash

    references to serving and food experiences

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

    actions being performed

    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
    .
    -0.49
    ord
    -0.46
    --
    -0.46
    –
    -0.45
    -
    -0.44
    ,
    -0.41
    —
    -0.41
     a
    -0.40
    hi
    -0.40
     –
    -0.39
    POSITIVE LOGITS
    NameInMap
    1.07
    ChildScrollView
    1.00
    SharedCtor
    0.99
     Efq
    0.97
    ViewFeatures
    0.97
    AndEndTag
    0.94
     referenties
    0.92
     transférez
    0.91
    ConstraintMaker
    0.89
    AddTagHelper
    0.88
    Activations Density 9.215%

    No Known Activations