© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14437
    Prev
    Next
    INDEX
    Explanations

    enumerated lists or references to external documents and some typesetting elements

    oai_token-act-pair · gemini-2.0-flash

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AndEndTag
    -0.55
    RegistryLite
    -0.54
    :✨
    -0.51
    gin
    -0.48
    newBuilder
    -0.45
    เทศ
    -0.44
    bolista
    -0.43
    ituri
    -0.43
     bgcolor
    -0.43
     كومونز
    -0.43
    POSITIVE LOGITS
    цездатний
    0.69
     fadeIn
    0.64
    Autoritní
    0.63
     jScrollPane
    0.62
    Personensuche
    0.60
    UTERS
    0.59
    __]
    0.59
     esterni
    0.59
    ]")]
    0.58
    autique
    0.57
    Activations Density 2.862%

    No Known Activations