© 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. 11454
    Prev
    Next
    INDEX
    Explanations

    words associated with customer service interactions, particularly when the customer has a complaint or issue.

    oai_token-act-pair · gemini-2.0-flash

    law enforcement

    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
    aarrggbb
    -0.59
    ftagPool
    -0.54
    didSet
    -0.49
     الحره
    -0.49
     wireType
    -0.49
     propOrder
    -0.48
     typelib
    -0.47
    ობ
    -0.46
     <=",
    -0.46
    CDCl
    -0.46
    POSITIVE LOGITS
     agents
    1.76
     agent
    1.69
     Agents
    1.58
     Agent
    1.54
    agent
    1.41
     AGENTS
    1.41
    Agents
    1.39
    agents
    1.38
     AGENT
    1.38
    Agent
    1.37
    Activations Density 2.387%

    No Known Activations