© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13005
    Prev
    Next
    INDEX
    Explanations

    positive adjectives with nouns.

    oai_token-act-pair · gemini-2.0-flash

    great

    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
    Great
    -1.23
     Great
    -1.16
    great
    -1.11
    GREAT
    -1.10
     GREAT
    -1.05
     great
    -1.01
     greatness
    -0.79
    tvguidetime
    -0.74
    TestTools
    -0.73
    RegressionTest
    -0.72
    POSITIVE LOGITS
     disambiguazione
    0.54
     cast
    0.48
    ReusableCell
    0.47
    BUSY
    0.47
    WithIOException
    0.45
     Dupont
    0.45
    luß
    0.45
    Aholisi
    0.44
    ידי
    0.43
     isinstance
    0.43
    Activations Density 3.596%

    No Known Activations