© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8119
    Prev
    Next
    INDEX
    Explanations

    the word "compact" in a mathematical or political context

    oai_token-act-pair · gemini-2.0-flash

    compact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    WithIOException
    -0.94
     tartalomajánló
    -0.91
     gynhyrchwyd
    -0.86
     برانيه
    -0.86
    mobileqq
    -0.85
    })]
    -0.84
    oredCriteria
    -0.84
    AddTagHelper
    -0.83
     ostavi
    -0.82
     myſelf
    -0.82
    POSITIVE LOGITS
     the
    0.65
    s
    0.60
    OWSKI
    0.56
    isasi
    0.55
     are
    0.55
    ,
    0.53
     even
    0.52
     that
    0.51
    ulement
    0.50
     pengh
    0.50
    Activations Density 1.375%

    No Known Activations