© 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. 16097
    Prev
    Next
    INDEX
    Explanations

    mentions of code, customer satisfaction, and names paired with colon

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
     my
    -3.11
     mijn
    -2.14
     meiner
    -2.08
     meines
    -2.02
    my
    -1.94
     моего
    -1.91
     meu
    -1.88
     mojej
    -1.86
     моих
    -1.86
     minha
    -1.84
    POSITIVE LOGITS
     mis
    0.62
     }}"></
    0.54
     Trouver
    0.51
    tersebut
    0.49
    mis
    0.49
    gemeester
    0.48
    plish
    0.47
     Mémoires
    0.46
     européennes
    0.45
    তথ্যসূত্র
    0.45
    Activations Density 3.555%

    No Known Activations