© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11235
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting desire or ability to do something important, such as a person "can open" something or "want to find" something, especially related to keys, doors and memory.

    oai_token-act-pair · gemini-2.0-flash

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ↵↵
    -0.56
     he
    -0.45
     o
    -0.43
    He
    -0.42
     voud
    -0.42
     
    -0.42
    van
    -0.41
     I
    -0.41
    be
    -0.40
     He
    -0.40
    POSITIVE LOGITS
     >=",
    1.16
    UrlResolution
    1.14
    TintMode
    1.05
    OGND
    1.04
    adpleegd
    1.02
     estekak
    0.97
    writeFieldEnd
    0.92
     AssemblyTitle
    0.91
     transfieras
    0.91
    extAlignment
    0.91
    Activations Density 0.798%

    No Known Activations