© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10180
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially C code containing definitions and hexadecimal values

    oai_token-act-pair · gemini-2.0-flash

    code/scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     auroit
    -1.15
     would
    -1.13
     feroit
    -1.13
     could
    -1.12
     étoient
    -1.10
     avoient
    -1.10
     can
    -1.09
     will
    -1.08
    berdayakan
    -1.08
     enfans
    -1.05
    POSITIVE LOGITS
     covalent
    0.56
     lunatic
    0.55
     hemis
    0.55
     syno
    0.55
     shiver
    0.55
     parapet
    0.54
     radiance
    0.54
     Philist
    0.53
     parlour
    0.53
     moor
    0.53
    Activations Density 32.387%

    No Known Activations