© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 14998
    Prev
    Next
    INDEX
    Explanations

    words related to possession and personal pronouns, especially when combined with references to society and personal expression.

    oai_token-act-pair · gemini-2.0-flash

    Personal opinion

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Efq
    -0.64
    saraba
    -0.63
     дописавши
    -0.60
    WebVitals
    -0.56
     <>",
    -0.54
     obstante
    -0.54
     becauſe
    -0.54
     iſt
    -0.54
    PullParser
    -0.52
     hjem
    -0.52
    POSITIVE LOGITS
     صوتيه
    0.58
    QMetaType
    0.57
    UserScript
    0.57
     BoxFit
    0.56
    skjaer
    0.52
    ExecuteNonQuery
    0.51
    нцип
    0.50
    gridy
    0.49
     nakalista
    0.49
     reger
    0.49
    Activations Density 0.387%

    No Known Activations