© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8827
    Prev
    Next
    INDEX
    Explanations

    the modals "may," "could," "would" and "should" and the phrases which use those verbs

    oai_token-act-pair · gemini-2.0-flash

    ha

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ArrowToggle
    -0.76
     resourceCulture
    -0.76
    DataAnnotations
    -0.72
    WebVitals
    -0.72
     Monfieur
    -0.70
    IntoConstraints
    -0.68
    findpost
    -0.67
     Мексичка
    -0.65
    ✭✭
    -0.65
     tslint
    -0.65
    POSITIVE LOGITS
     ha
    1.97
     Ha
    1.74
    Ha
    1.66
     HA
    1.64
    HA
    1.41
    ha
    1.35
     Hav
    1.21
     HAV
    1.15
     haver
    1.12
    哈
    1.12
    Activations Density 1.354%

    No Known Activations