© 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. 11885
    Prev
    Next
    INDEX
    Explanations

    content describing aftermarket car modifications and tuning

    oai_token-act-pair · gemini-2.0-flash

    car tuning

    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
    WarningLevel
    -0.55
    numerusform
    -0.50
     resourceCulture
    -0.48
     stress
    -0.48
    memoized
    -0.47
    teza
    -0.47
    StoryboardSegue
    -0.47
    XmlSchema
    -0.46
     CONNECT
    -0.44
    stres
    -0.44
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.63
    scalatest
    0.59
    elemField
    0.58
    phosa
    0.57
    pogon
    0.55
    ipient
    0.55
    QPalette
    0.54
    []
    0.53
     Савезне
    0.52
     дописавши
    0.52
    Activations Density 0.522%

    No Known Activations