© 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. 10186
    Prev
    Next
    INDEX
    Explanations

    the string "tmp" followed by a number

    oai_token-act-pair · gemini-2.0-flash

    tmp

    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
    tmp
    -2.17
     tmp
    -1.95
    Tmp
    -1.20
     temp
    -1.10
    TMP
    -1.00
    temp
    -0.96
     temporary
    -0.96
     Temporary
    -0.92
    Temp
    -0.89
     Temp
    -0.88
    POSITIVE LOGITS
    évaluateur
    0.75
    WithIOException
    0.65
     rapat
    0.60
     تضيفلها
    0.60
    writeFieldEnd
    0.59
    OGND
    0.58
    bootstrapcdn
    0.51
     dataSnapshot
    0.50
    就知道
    0.50
     negativas
    0.49
    Activations Density 0.545%

    No Known Activations