© 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. 10539
    Prev
    Next
    INDEX
    Explanations

    the substring "Str"

    oai_token-act-pair · gemini-2.0-flash

    Str

    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
     sure
    -0.42
     по
    -0.41
     ristoranti
    -0.41
     St
    -0.40
     at
    -0.40
     ракет
    -0.37
    厄
    -0.37
     pār
    -0.36
     P
    -0.35
    ranes
    -0.35
    POSITIVE LOGITS
     itſelf
    1.04
     myſelf
    0.98
    Controllo
    0.92
     Bourgoin
    0.92
    setViewportView
    0.92
     للاسماء
    0.92
    WebVitals
    0.90
     ſche
    0.88
     themſelves
    0.88
     uſe
    0.88
    Activations Density 0.861%

    No Known Activations