© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4368
    Prev
    Next
    INDEX
    Explanations

    words with numbers and dates

    oai_token-act-pair · gemini-2.0-flash

    uniqueness

    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
    particular
    -0.82
     particular
    -0.81
    Particular
    -0.72
     Specific
    -0.71
     Particular
    -0.70
     specific
    -0.69
    Specific
    -0.66
     PARTICULAR
    -0.63
    specific
    -0.62
    typical
    -0.60
    POSITIVE LOGITS
     unique
    0.90
    unique
    0.85
    TagMode
    0.85
     Unique
    0.80
     uniquely
    0.75
    Unique
    0.74
     unieke
    0.68
     uniques
    0.66
    IsContent
    0.64
     UNIQUE
    0.64
    Activations Density 12.675%

    No Known Activations