© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4293
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    proofs and code snippets

    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
    TypedDataSet
    -0.57
    նակ
    -0.52
     oprot
    -0.48
    DockStyle
    -0.47
    usercontent
    -0.45
    httphttps
    -0.45
    Хьажоргаш
    -0.44
     sorte
    -0.44
    ager
    -0.41
     ""],
    -0.41
    POSITIVE LOGITS
    ([...
    0.58
    EndInit
    0.57
     also
    0.57
     كمان
    0.56
     RestTemplate
    0.56
    SpringBootTest
    0.54
    SourceChecksum
    0.54
    ostic
    0.53
    тельности
    0.53
    chlag
    0.53
    Activations Density 14.117%

    No Known Activations