© 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. 16095
    Prev
    Next
    INDEX
    Explanations

    phrases about things that happen or exist online and their effects

    oai_token-act-pair · gemini-2.0-flash

    non-English words

    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
    +#+
    -0.88
    tanleria
    -0.87
    IndentedString
    -0.74
    FormTagHelper
    -0.73
     Affiliations
    -0.73
     صوتيه
    -0.71
     EconPapers
    -0.70
     MonoBehaviour
    -0.70
    EndGlobalSection
    -0.69
    ExtendWith
    -0.68
    POSITIVE LOGITS
    gn
    0.42
    UnknownFieldSet
    0.40
    我有
    0.39
    ీ
    0.38
    Clik
    0.36
    ımı
    0.35
    гут
    0.35
     bawah
    0.35
     combinação
    0.34
     résolution
    0.33
    Activations Density 0.626%

    No Known Activations