© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6555
    Prev
    Next
    INDEX
    Explanations

    capitalized jargon words, especially those related to legal or anime contexts

    oai_token-act-pair · gemini-2.0-flash

    Sci-fi "Argo" and "Nautilus"

    np_max-act · 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
     ―――――
    -2.77
     ་་
    -2.73
     itſelf
    -2.67
     myſelf
    -2.36
     Efq
    -2.34
     Houſe
    -2.28
     Anſ
    -2.16
     Reſ
    -2.14
     photolibrary
    -2.13
     Majefty
    -2.13
    POSITIVE LOGITS
     A
    1.59
     I
    1.51
     
    1.46
     G
    1.45
     K
    1.44
     T
    1.42
     S
    1.42
     The
    1.41
     N
    1.40
     L
    1.38
    Activations Density 4.901%

    No Known Activations