© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9967
    Prev
    Next
    INDEX
    Explanations

    mentions of a variety of unrelated topics and parts of speech, suggesting it's poorly trained

    oai_token-act-pair · gemini-2.0-flash

    Abbreviated units

    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
    __":
    -0.95
     Вікі
    -0.85
     AppModule
    -0.82
    __":
    -0.82
    __':
    -0.80
    Demografie
    -0.79
    HasAnnotation
    -0.76
    الحياه
    -0.76
    сылкі
    -0.75
    LOYEES
    -0.75
    POSITIVE LOGITS
    V
    0.48
    B
    0.48
    dB
    0.48
    GB
    0.47
    W
    0.47
    cm
    0.45
    L
    0.44
    N
    0.44
    nm
    0.44
    g
    0.43
    Activations Density 1.713%

    No Known Activations