© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7923
    Prev
    Next
    INDEX
    Explanations

    the titles and introductory paragraphs of patent applications or technical papers

    oai_token-act-pair · gemini-2.0-flash

    Prior art for inventions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     First
    -0.75
     Set
    -0.68
    First
    -0.67
    SharedCtor
    -0.63
     Self
    -0.60
    Self
    -0.60
     Free
    -0.58
     Terbaru
    -0.58
     Home
    -0.57
     Second
    -0.57
    POSITIVE LOGITS
     تكبرها
    0.66
     Target
    0.63
     Animal
    0.60
     Pagan
    0.60
    Command
    0.59
     Mission
    0.59
     AFFECT
    0.58
     Enemy
    0.58
     Task
    0.57
     Ancient
    0.56
    Activations Density 14.574%

    No Known Activations