© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13723
    Prev
    Next
    INDEX
    Explanations

    a cluster of words related to politeness, gratitude, and possibly non-native English writing.

    oai_token-act-pair · gemini-2.0-flash

    advice and opinions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     femininas
    -0.53
    RegressionTest
    -0.52
     preghi
    -0.48
     tarko
    -0.47
    Ursula
    -0.47
     căr
    -0.47
     azioni
    -0.45
     tecnici
    -0.45
     giudi
    -0.45
     ricordi
    -0.45
    POSITIVE LOGITS
    发表于
    0.67
    AnimationsModule
    0.65
    "}";
    0.64
    gameserver
    0.61
    EndGlobalSection
    0.61
     <=",
    0.60
    CUSS
    0.59
    HomeAsUpEnabled
    0.58
    XmlAccessType
    0.56
    ESSIONAL
    0.56
    Activations Density 2.195%

    No Known Activations