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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7787
    Prev
    Next
    INDEX
    Explanations

    code snippets and discourse about software licensing or technical specifications

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -1.61
     myſelf
    -1.57
    ^(@)
    -1.53
     Monfieur
    -1.48
    bibfield
    -1.46
     $_"
    -1.45
     Jefus
    -1.41
     photolibrary
    -1.41
    BibitemShut
    -1.41
     Majefty
    -1.39
    POSITIVE LOGITS
    <bos>
    1.37
    for
    1.18
    in
    1.15
    the
    1.12
    and
    1.10
    of
    1.09
    a
    1.06
    we
    1.05
    if
    1.02
    ↵↵
    1.01
    Activations Density 6.965%

    No Known Activations