© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9074
    Prev
    Next
    INDEX
    Explanations

    Italian or Spanish language fragments in the English text.

    oai_token-act-pair · gemini-2.0-flash

    Italian and French

    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
    Autoritní
    -0.61
    IntoConstraints
    -0.56
    ̍t
    -0.52
     Waray
    -0.47
    Leben
    -0.47
    AutoresizingMask
    -0.47
    Източници
    -0.46
    olidated
    -0.45
    GeneratedValue
    -0.44
    icherung
    -0.43
    POSITIVE LOGITS
    DeleteBehavior
    0.65
     /\.(
    0.59
    AutoField
    0.57
    )_/¯
    0.55
    URLEncoder
    0.52
    ínguez
    0.52
    atrician
    0.51
    ientôt
    0.50
    loroethene
    0.50
     ragazzi
    0.50
    Activations Density 0.278%

    No Known Activations