© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11413
    Prev
    Next
    INDEX
    Explanations

    instances of people referencing code they are writing and the issues they are facing

    oai_token-act-pair · gemini-2.0-flash

    Becoming or getting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    FailureListener
    -0.51
     sağlar
    -0.46
     käytet
    -0.45
    িন
    -0.43
    lanır
    -0.42
     ditemukan
    -0.40
    你不是
    -0.39
     réussi
    -0.39
    デレ
    -0.39
    Nomenclature
    -0.39
    POSITIVE LOGITS
     getting
    1.71
     taking
    1.51
     gaining
    1.47
     forming
    1.45
     becoming
    1.43
     doing
    1.41
     developing
    1.38
     making
    1.38
     coming
    1.37
     turning
    1.34
    Activations Density 3.396%

    No Known Activations