© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    highly political text, specifically arguments about healthcare reform.

    oai_token-act-pair · gemini-2.0-flash

    healthcare insurance

    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
     Covers
    -1.02
     Covering
    -1.00
     cover
    -1.00
     covers
    -0.98
    Covers
    -0.96
    Cover
    -0.95
    Personendaten
    -0.94
    COVER
    -0.92
    covers
    -0.92
     Cover
    -0.91
    POSITIVE LOGITS
    g
    0.38
    実
    0.35
    add
    0.35
     PAR
    0.35
    ″]
    0.34
    Repositorio
    0.33
     par
    0.31
     ans
    0.31
    yy
    0.31
     yêu
    0.31
    Activations Density 2.358%

    No Known Activations