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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14280
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating complexity and a negative sentiment.

    oai_token-act-pair · gemini-2.0-flash

    problems and difficulties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     ويكيپيديا
    -0.72
    yntaxException
    -0.71
     تضيفلها
    -0.70
    didSet
    -0.69
    abestanden
    -0.69
    AnchorStyles
    -0.66
    
    -0.65
    OwnProperty
    -0.63
     Савезне
    -0.61
    igshid
    -0.61
    POSITIVE LOGITS
    pre
    0.49
    </>
    0.47
    stdafx
    0.46
     pre
    0.45
     prä
    0.45
     pré
    0.45
    ıklı
    0.45
     turbines
    0.43
     tranquillo
    0.42
     Tamp
    0.42
    Activations Density 18.624%

    No Known Activations