© 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. 14800
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of how to do or achieve something

    oai_token-act-pair · gemini-2.0-flash

    way

    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
     NSCoder
    -0.99
    AndEndTag
    -0.90
    !*\
    -0.87
    thâu
    -0.86
     Catawiki
    -0.85
    RegistryLite
    -0.85
    +#+#
    -0.85
    onAttach
    -0.84
     /\.
    -0.84
     ExecuteAsync
    -0.83
    POSITIVE LOGITS
     you
    0.52
    ly
    0.50
     looking
    0.50
     to
    0.49
    Looking
    0.48
    Int
    0.47
    sm
    0.47
     spend
    0.46
    いざ
    0.46
    looking
    0.46
    Activations Density 1.336%

    No Known Activations