© 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. 3517
    Prev
    Next
    INDEX
    Explanations

    code with booleans, loops, null values

    oai_token-act-pair · gemini-2.0-flash

    null

    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
     jScrollPane
    -0.60
     m
    -0.52
     du
    -0.48
     da
    -0.47
     Sister
    -0.45
    synthesize
    -0.45
    ljeno
    -0.43
     B
    -0.43
     lo
    -0.42
     free
    -0.41
    POSITIVE LOGITS
    MigrationBuilder
    1.00
    RenderAtEndOf
    0.98
     Majefty
    0.82
     Efq
    0.81
    awtextra
    0.80
    CloseOperation
    0.80
     onCreateView
    0.79
     purpoſe
    0.77
     fubject
    0.75
     iſt
    0.74
    Activations Density 3.079%

    No Known Activations