© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3082
    Prev
    Next
    INDEX
    Explanations

    parts of HTML tables and code blocks

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     nakalista
    -1.02
    tagHelperRunner
    -0.99
     EconPapers
    -0.97
     Roskov
    -0.91
    rungsseite
    -0.91
    windowFixed
    -0.90
     estekak
    -0.87
    richTextPanel
    -0.85
     '\\;'
    -0.82
     насељу
    -0.81
    POSITIVE LOGITS
     
    1.34
    hæ
    0.35
    ğın
    0.34
    Garantie
    0.33
    pæ
    0.32
     haga
    0.31
    ина
    0.31
     encantan
    0.31
    fetching
    0.31
     ilç
    0.31
    Activations Density 1.445%

    No Known Activations