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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 850
    Prev
    Next
    INDEX
    Explanations

    mentions of soccer teams and people

    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
     تضيفلها
    -0.70
     BoxDecoration
    -0.69
     Akismet
    -0.65
    tonode
    -0.64
     <<<<<<<<<<<<<<
    -0.61
    новниш
    -0.60
    AddHtmlAttribute
    -0.58
    fjspx
    -0.56
    seteq
    -0.54
     noqa
    -0.54
    POSITIVE LOGITS
     transfieras
    0.48
     Cientí
    0.47
    ("")]
    0.46
     scientifique
    0.46
     suprême
    0.42
     domy
    0.42
    UnitTesting
    0.41
     jurídico
    0.41
     científicos
    0.40
     ouver
    0.40
    Activations Density 0.525%

    No Known Activations