© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1408
    Prev
    Next
    INDEX
    Explanations

    website URL references and editing terms

    oai_token-act-pair · gemini-2.0-flash

    article titles

    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
     يتيمه
    -0.90
    awtextra
    -0.79
    featureID
    -0.79
     Roskov
    -0.76
    setVerticalGroup
    -0.75
    LLocation
    -0.72
     esternos
    -0.68
    GEBURTSDATUM
    -0.68
    principalTable
    -0.67
     дописавши
    -0.67
    POSITIVE LOGITS
    tisol
    0.54
    ("*");
    0.52
     pura
    0.47
     Ayu
    0.45
     []),
    0.45
     exemples
    0.45
    iniest
    0.43
    %"),
    0.42
    着了
    0.42
     getPosition
    0.41
    Activations Density 23.239%

    No Known Activations