© 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. 10967
    Prev
    Next
    INDEX
    Explanations

    words that describe physical connection, physical shape, or fitting in with a design

    oai_token-act-pair · gemini-2.0-flash

    attached

    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
    <bos>
    -0.73
    WithIOException
    -0.56
    PYX
    -0.54
    ">//
    -0.54
     survie
    -0.50
     attached
    -0.49
    SourceChecksum
    -0.48
    Attached
    -0.46
    jspb
    -0.46
     initComponents
    -0.45
    POSITIVE LOGITS
    पया
    0.70
     gynhyrchwyd
    0.63
     getLogin
    0.62
     hefyd
    0.60
    Enllaços
    0.60
     Crowd
    0.60
    lohn
    0.59
    AutoScaleMode
    0.59
     lobby
    0.57
     Marqu
    0.56
    Activations Density 2.996%

    No Known Activations