© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as "case", "default", "} else if", "UNRECOGNIZED", and "rawValue".

    oai_token-act-pair · gemini-2.0-flash

    Conditional statements

    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
    rohr
    -0.49
     Mariano
    -0.45
     Statisti
    -0.44
     Kegiatan
    -0.43
     raffredd
    -0.43
    min
    -0.42
     realized
    -0.42
    MongoClient
    -0.42
     keskus
    -0.41
     yanında
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.83
    rungsseite
    0.80
     snippetHide
    0.78
     متعلقه
    0.78
    oredCriteria
    0.76
    ArrowToggle
    0.69
     ProtoMessage
    0.67
     himo
    0.66
    matchCondition
    0.65
     iNdEx
    0.65
    Activations Density 1.149%

    No Known Activations