© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3801
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup for mathematical symbols and formulae

    oai_token-act-pair · gemini-2.0-flash

    say 'the ending }'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    曖昧さ回避
    -0.66
    ?».
    -0.64
    MLLoader
    -0.63
     архивлан
    -0.60
    )».
    -0.60
     générations
    -0.59
    reactstrap
    -0.57
     varandra
    -0.57
    ).</
    -0.57
    Personensuche
    -0.56
    POSITIVE LOGITS
     are
    0.67
     can
    0.64
    ='\
    0.58
    can
    0.58
    isu
    0.57
     Sit
    0.57
     sits
    0.53
     focuses
    0.52
     is
    0.52
     ab
    0.52
    Activations Density 4.098%

    No Known Activations