© 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. 3216
    Prev
    Next
    INDEX
    Explanations

    author names and publication years enclosed in square brackets and parentheses with extra symbols (@, #, =).

    oai_token-act-pair · gemini-2.0-flash

    Citations in scientific papers

    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
     Donahue
    -0.88
     Kearns
    -0.82
     Schulte
    -0.82
     Baumann
    -0.80
     Madsen
    -0.79
     Jaffe
    -0.77
     Metzger
    -0.77
     McClure
    -0.77
     Christiansen
    -0.77
     McGowan
    -0.76
    POSITIVE LOGITS
    lccn
    0.35
     Plots
    0.35
     Filler
    0.34
    LLocation
    0.34
     BoxDecoration
    0.33
     Interpreter
    0.33
     Estudi
    0.32
     Flap
    0.32
     Hypothe
    0.31
     Descriptors
    0.31
    Activations Density 7.406%

    No Known Activations