© 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. 3243
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes

    oai_token-act-pair · gemini-2.0-flash

    dc ca

    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
    ंदीखरीदारी
    -0.85
     newBuilder
    -0.80
    fjspx
    -0.78
    atguigu
    -0.75
    WireFormatLite
    -0.73
     SwitchCompat
    -0.72
     دریافت‌شده
    -0.71
     esternos
    -0.69
     betweenstory
    -0.69
    drawal
    -0.69
    POSITIVE LOGITS
    thâu
    0.46
    sey
    0.40
    = 
    0.40
     asemenea
    0.40
    &
    0.39
    istics
    0.38
     nawr
    0.38
     ModelExpression
    0.38
    ma
    0.37
    ex
    0.37
    Activations Density 6.458%

    No Known Activations