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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10375
    Prev
    Next
    INDEX
    Explanations

    a combination of numbers, hyphens, parentheses, forward slashes and decimal points

    oai_token-act-pair · gemini-2.0-flash

    Spelled-out numbers

    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
     étoient
    -0.56
    <bos>
    -0.55
     varandra
    -0.49
     enfans
    -0.48
     avoient
    -0.46
     étoit
    -0.45
     världen
    -0.43
     militaires
    -0.41
     industriels
    -0.41
     supérieurs
    -0.41
    POSITIVE LOGITS
    0
    1.21
    ０
    0.81
    nine
    0.79
     eighteen
    0.77
     
    0.77
     ten
    0.75
     nine
    0.75
     seven
    0.75
     fifteen
    0.74
     fourteen
    0.73
    Activations Density 3.592%

    No Known Activations