© 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. 1245
    Prev
    Next
    INDEX
    Explanations

    This neuron finds Italian phrases and, to a lesser extent, references to war and/or opera

    oai_token-act-pair · gemini-2.0-flash

    Italian adjectives

    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
    -0.62
    AddTagHelper
    -0.62
     snippetHide
    -0.53
    /**
    -0.52
    lète
    -0.51
     racial
    -0.51
    ########.
    -0.48
    StringProperty
    -0.48
    RPD
    -0.48
     Fid
    -0.47
    POSITIVE LOGITS
     popolare
    0.64
     fotografico
    0.64
     ambientale
    0.60
     umana
    0.60
     mentale
    0.57
     alimentare
    0.57
     naturelle
    0.56
     italienne
    0.56
    gany
    0.55
     naturale
    0.54
    Activations Density 1.048%

    No Known Activations