© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14848
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conversation and debate

    oai_token-act-pair · gemini-2.0-flash

    Discussions and debates

    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
    PhysRevLett
    -0.47
    Datuak
    -0.43
     løpet
    -0.42
     notícias
    -0.42
     titul
    -0.40
     venganza
    -0.39
    hülle
    -0.38
    Mojo
    -0.38
    şa
    -0.38
     quiso
    -0.38
    POSITIVE LOGITS
     dialogue
    1.28
     debate
    1.19
     dialog
    1.19
     discussion
    1.18
     DIALOG
    1.09
     Dialogue
    1.09
    dialogue
    1.08
     dialogues
    1.07
     debates
    1.05
    debate
    1.03
    Activations Density 4.665%

    No Known Activations