© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8334
    Prev
    Next
    INDEX
    Explanations

    the word "association" and words related to openness or staying in a place

    oai_token-act-pair · gemini-2.0-flash

    relationships/connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.64
     stay
    -0.57
     for
    -0.57
     much
    -0.56
    Literatuur
    -0.55
    ing
    -0.54
     but
    -0.53
    ,
    -0.52
    ená
    -0.52
     stage
    -0.51
    POSITIVE LOGITS
     GenerationType
    1.13
    parsedMessage
    1.13
    MigrationBuilder
    1.13
    Personendaten
    1.05
     disambiguazione
    1.02
    +#+#
    1.02
    sizeCache
    1.02
    makeConstraints
    1.02
    createCanvas
    1.00
    Vidite
    0.98
    Activations Density 3.538%

    No Known Activations