© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1624
    Prev
    Next
    INDEX
    Explanations

    language about question and discussion, often about a group of people

    oai_token-act-pair · gemini-2.0-flash

    ask

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    uxxxx
    -0.60
    hoeddwyd
    -0.57
    rollment
    -0.54
    ]--;
    -0.54
    ueroa
    -0.54
    Concerns
    -0.53
    rolid
    -0.52
     Potsdam
    -0.52
    issue
    -0.52
    aarrggbb
    -0.52
    POSITIVE LOGITS
     ask
    2.17
     Ask
    1.91
    Ask
    1.83
     asking
    1.82
     asks
    1.73
     asked
    1.72
    ask
    1.70
     Asking
    1.59
     ASK
    1.55
    asking
    1.55
    Activations Density 3.427%

    No Known Activations