© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15357
    Prev
    Next
    INDEX
    Explanations

    names of people, references to media, the word the and the word "the" followed by a comma, numbers, and some verbs

    oai_token-act-pair · gemini-2.0-flash

    Summaries of various topics

    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
     незавершена
    -0.91
    protoimpl
    -0.81
    EDEFAULT
    -0.79
    AnimationsModule
    -0.78
    AxisAlignment
    -0.78
     BIBSYS
    -0.74
    MemoryWarning
    -0.73
     ویکی‌پدیا
    -0.73
    rungsseite
    -0.73
    Portale
    -0.73
    POSITIVE LOGITS
     vu
    0.47
    initializer
    0.42
    v
    0.40
     Curtis
    0.39
    lagt
    0.39
    िन्न
    0.39
    subpackage
    0.38
     Riddle
    0.38
     cu
    0.38
    Thrown
    0.38
    Activations Density 3.311%

    No Known Activations