© 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. 15272
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     Zero
    -2.20
     zero
    -2.16
    Zero
    -2.06
    zero
    -1.97
     empty
    -1.97
     ZERO
    -1.95
     Empty
    -1.93
     Null
    -1.90
    Empty
    -1.83
     null
    -1.82
    POSITIVE LOGITS
    prisma
    0.46
     Vogel
    0.46
    τός
    0.44
    ramanian
    0.43
     cánh
    0.43
    issens
    0.42
    ടു
    0.41
     пого
    0.41
    urazione
    0.41
    balleur
    0.41
    Activations Density 2.763%

    No Known Activations