© 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. 3701
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is stating what they 'can see'

    oai_token-act-pair · 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
     saw
    -2.17
    saw
    -1.97
     Saw
    -1.97
    Saw
    -1.91
     seen
    -1.65
     seeing
    -1.62
     Seeing
    -1.59
     SAW
    -1.53
     Seen
    -1.52
    seen
    -1.49
    POSITIVE LOGITS
    ThemeOverlay
    0.73
     Roskov
    0.71
     se
    0.69
    complexContent
    0.60
    CloseOperation
    0.57
    ThroughAttribute
    0.54
    intios
    0.51
    GEBURTSDATUM
    0.50
    новништво
    0.50
     rowspan
    0.49
    Activations Density 2.032%

    No Known Activations