© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10536
    Prev
    Next
    INDEX
    Explanations

    complex German sentences using multiple verbs, especially modal verbs, and references to writing letters

    oai_token-act-pair · gemini-2.0-flash

    German technical information

    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
    +#+#
    -0.97
    setVerticalGroup
    -0.96
     typelib
    -0.82
     beginnetje
    -0.82
     Reſ
    -0.80
     ―――――
    -0.78
     Efq
    -0.77
    ImageContext
    -0.77
    AndEndTag
    -0.75
     مشين
    -0.75
    POSITIVE LOGITS
    .
    0.36
     nun
    0.35
     Gummies
    0.35
    ster
    0.34
     tố
    0.34
    Malformed
    0.33
     ter
    0.32
    stel
    0.32
     stationnement
    0.32
     Durch
    0.31
    Activations Density 4.398%

    No Known Activations