© 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. 12651
    Prev
    Next
    INDEX
    Explanations

    numbers and dates, often in legal or medical contexts

    oai_token-act-pair · gemini-2.0-flash

    nine

    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
    SharedCtor
    -0.67
     Normdatei
    -0.64
    Datuak
    -0.61
    Geplaatst
    -0.61
    rungsseite
    -0.57
    8
    -0.56
     nahilalakip
    -0.55
    OGND
    -0.54
    hassee
    -0.52
    Obrázky
    -0.51
    POSITIVE LOGITS
     nine
    1.33
    9
    1.26
     ninety
    1.20
     Nine
    1.16
     ninth
    1.09
     nueve
    1.02
     Ninth
    1.01
     NINE
    0.99
    Nine
    0.96
    九
    0.96
    Activations Density 0.931%

    No Known Activations