© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16183
    Prev
    Next
    INDEX
    Explanations

    the word "Good."

    oai_token-act-pair · gemini-2.0-flash

    good

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     good
    -0.70
    GOOD
    -0.67
     initComponents
    -0.64
     GOOD
    -0.64
    good
    -0.63
     Мексичка
    -0.60
    Good
    -0.60
     ră
    -0.59
     buon
    -0.59
     Good
    -0.57
    POSITIVE LOGITS
    #+#
    0.65
    Personendaten
    0.52
    sidemargin
    0.48
    interopRequire
    0.47
    contentLoaded
    0.45
     trás
    0.44
    FunctionFlags
    0.42
    ParallelGroup
    0.42
    __*/
    0.42
     defaultstate
    0.41
    Activations Density 0.270%

    No Known Activations