© 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. 16189
    Prev
    Next
    INDEX
    Explanations

    bible verses and references to readings

    oai_token-act-pair · gemini-2.0-flash

    Biblical texts

    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
    Sucesor
    -0.74
     createState
    -0.70
     estimés
    -0.64
    djangoproject
    -0.63
     незавершена
    -0.62
     Мексичка
    -0.62
    abestanden
    -0.62
     HasFactory
    -0.60
    FieldNumber
    -0.60
    تقاوى
    -0.60
    POSITIVE LOGITS
    RegressionTest
    0.73
    zzleHttp
    0.63
     Jefus
    0.60
     Theſe
    0.53
     avoient
    0.53
     becauſe
    0.53
     quæ
    0.52
     myſelf
    0.52
     eorum
    0.52
     noires
    0.50
    Activations Density 1.486%

    No Known Activations