© 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. 6754
    Prev
    Next
    INDEX
    Explanations

    a mix of swear words along with some words like "first," "dad," and percentages that look like noise

    oai_token-act-pair · gemini-2.0-flash

    say punctuation marks

    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
    !
    -1.66
    Personendaten
    -0.87
    
    -0.82
    archiviato
    -0.81
     '{@
    -0.78
    ！
    -0.77
     !
    -0.75
    tagHelperRunner
    -0.73
    :)
    -0.72
    __(/*!
    -0.70
    POSITIVE LOGITS
    的呢
    0.46
    arrer
    0.45
    asants
    0.45
    ghis
    0.44
     espoir
    0.44
     PrintWriter
    0.44
     ?...
    0.43
     tuyên
    0.43
    entado
    0.43
     schermata
    0.42
    Activations Density 1.519%

    No Known Activations