© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12741
    Prev
    Next
    INDEX
    Explanations

    latex code

    oai_token-act-pair · gemini-2.0-flash

    backslash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Skocz
    -0.65
    日閲覧
    -0.47
    GraphicsUnit
    -0.41
     CWE
    -0.40
     assured
    -0.40
    findpost
    -0.40
    CloseOperation
    -0.39
     DEFEND
    -0.39
     wyma
    -0.38
    ShortName
    -0.38
    POSITIVE LOGITS
    VersionUID
    0.57
    bitField
    0.56
     Diſ
    0.56
     propOrder
    0.56
    [:,:,
    0.56
    Erreferentziak
    0.55
    ANNES
    0.55
    createComponent
    0.55
     ProtoMessage
    0.55
    RefNanny
    0.54
    Activations Density 1.331%

    No Known Activations