© 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. 8614
    Prev
    Next
    INDEX
    Explanations

    technical writing discussing problems and solutions.

    oai_token-act-pair · gemini-2.0-flash

    technical language

    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
    Increased
    -0.65
    increased
    -0.63
     Increased
    -0.59
     متعلقه
    -0.57
    Enhanced
    -0.57
    Minim
    -0.56
    opti
    -0.56
     diminu
    -0.54
     Better
    -0.53
    Better
    -0.53
    POSITIVE LOGITS
    AccessorTable
    0.60
    SequentialGroup
    0.57
    hoes
    0.57
    Źródło
    0.56
     Agamemnon
    0.56
    aconda
    0.54
     rivets
    0.54
     pymongo
    0.54
    DllImport
    0.52
     fotográfica
    0.52
    Activations Density 9.168%

    No Known Activations