© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 4300
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and references to them

    oai_token-act-pair · gemini-2.0-flash

    say "b" words

    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
     B
    -1.24
    B
    -1.19
     BB
    -1.19
     Bl
    -1.16
     Б
    -1.16
    BB
    -1.12
    B
    -1.10
     Bi
    -1.07
     Bu
    -1.06
     Bo
    -1.05
    POSITIVE LOGITS
    queryInterface
    0.54
    expandindo
    0.52
     Winaray
    0.46
    minecraftforge
    0.44
    انيف
    0.44
    :✨
    0.42
     beginnetje
    0.41
     TextAlign
    0.40
    térature
    0.40
    tinya
    0.40
    Activations Density 53.941%

    No Known Activations