© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7703
    Prev
    Next
    INDEX
    Explanations

    words related to a place, combined with pronouns.

    oai_token-act-pair · gemini-2.0-flash

    somewhere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     displays
    -0.60
    setDisplay
    -0.59
     مط
    -0.58
    IntoConstraints
    -0.57
    ej
    -0.57
     ACH
    -0.56
     призна
    -0.56
     (£
    -0.55
    .
    -0.54
     Sitten
    -0.53
    POSITIVE LOGITS
     médicaux
    0.97
     scolaires
    0.96
     américains
    0.94
     sauvages
    0.93
     chrétien
    0.92
     supérieures
    0.92
     traditionnels
    0.90
     abstrait
    0.90
     fråga
    0.90
     actuels
    0.90
    Activations Density 1.309%

    No Known Activations