© 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. 14999
    Prev
    Next
    INDEX
    Explanations

    positive sentiment words, especially in the context of sports teams and players

    oai_token-act-pair · gemini-2.0-flash

    sports

    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
     AssemblyTitle
    -0.61
    ########.
    -0.60
     ***!
    -0.57
    HomeAsUpEnabled
    -0.55
    ViewImports
    -0.53
    prefixer
    -0.50
     médicale
    -0.49
    rdf
    -0.48
     expired
    -0.48
     vĩnh
    -0.47
    POSITIVE LOGITS
     незавершена
    0.74
    UnknownFieldSet
    0.65
     Normdatei
    0.61
    ліст
    0.58
    timent
    0.56
    ритори
    0.53
    daille
    0.52
    Portale
    0.52
     udaler
    0.50
     hậu
    0.48
    Activations Density 2.788%

    No Known Activations