© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10378
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate something has come to a standstill

    oai_token-act-pair · gemini-2.0-flash

    stop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     drive
    -0.55
    roupa
    -0.54
     drove
    -0.54
     Driven
    -0.54
    Бахар
    -0.53
    <bos>
    -0.52
     driven
    -0.52
     Waugh
    -0.51
    にな
    -0.51
    drive
    -0.50
    POSITIVE LOGITS
    intios
    0.76
     ferma
    0.65
    StructEnd
    0.63
     nahilalakip
    0.60
     fermo
    0.60
     slowing
    0.60
    Geplaatst
    0.60
    MigrationBuilder
    0.60
     arrêter
    0.59
     Stopping
    0.59
    Activations Density 0.990%

    No Known Activations