© 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. 897
    Prev
    Next
    INDEX
    Explanations

    connections and relations between characters, especially in religious or mythological contexts

    oai_token-act-pair · gemini-2.0-flash

    passages from books

    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
    ResumeLayout
    -0.67
    rungsseite
    -0.57
    Hentet
    -0.57
    prnewswire
    -0.56
    Kaynakça
    -0.55
    DotNetBar
    -0.54
     kasarigan
    -0.54
    complexType
    -0.52
    InputBorder
    -0.52
    دانشنامهٔ
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.53
    paravant
    0.52
     vastaan
    0.47
    entrevista
    0.47
     Pingback
    0.46
     웹툰
    0.46
     bParam
    0.45
    tehen
    0.45
    ις
    0.45
    claimer
    0.44
    Activations Density 1.599%

    No Known Activations