© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13235
    Prev
    Next
    INDEX
    Explanations

    the word "out" and its surrounding words and prepositions

    oai_token-act-pair · gemini-2.0-flash

    terms related to entrances or exits

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

    Building front/entrance

    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
    WireFormatLite
    -0.62
     leksikon
    -0.58
     esternos
    -0.57
    GraphicsUnit
    -0.57
    +:+
    -0.57
    MemoryWarning
    -0.56
     wireType
    -0.56
     autorytatywna
    -0.55
    JspWriter
    -0.53
    IBOutlet
    -0.52
    POSITIVE LOGITS
     front
    1.01
     FRONT
    0.80
    doors
    0.80
     doors
    0.80
    front
    0.79
    Front
    0.72
     Front
    0.72
    door
    0.72
    side
    0.69
     door
    0.69
    Activations Density 1.019%

    No Known Activations