© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3388
    Prev
    Next
    INDEX
    Explanations

    words related to car transmissions, especially shifters and controls

    oai_token-act-pair · gemini-2.0-flash

    cars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     trasmissione
    -0.52
     sauvages
    -0.51
     שוליים
    -0.49
     vastaan
    -0.49
     debout
    -0.46
    dolu
    -0.45
    Gizmos
    -0.45
     decorazione
    -0.45
     världen
    -0.44
    chequer
    -0.43
    POSITIVE LOGITS
     pinulongan
    0.83
    UnsafeEnabled
    0.71
    BASELINE
    0.68
    ="@+
    0.58
    uinal
    0.57
    HeaderText
    0.56
    Hozzáférés
    0.55
    twimg
    0.55
     wishing
    0.54
    WithIOException
    0.54
    Activations Density 20.796%

    No Known Activations