© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12499
    Prev
    Next
    INDEX
    Explanations

    legal citations

    oai_token-act-pair · gemini-2.0-flash

    Supp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     المعيارى
    -0.84
     MainAxisSize
    -0.81
     typelib
    -0.81
    ArgsConstructor
    -0.80
    #+#
    -0.80
    fjspx
    -0.76
    RegistryLite
    -0.75
     AssemblyCulture
    -0.74
     AssemblyProduct
    -0.73
    StructEnd
    -0.72
    POSITIVE LOGITS
    Eksterne
    0.59
    MUX
    0.54
    mehl
    0.51
     accompagné
    0.50
     eccl
    0.49
     arrêt
    0.48
     oplossing
    0.48
     paraître
    0.47
     sauf
    0.47
     bekym
    0.47
    Activations Density 1.558%

    No Known Activations