© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11606
    Prev
    Next
    INDEX
    Explanations

    language about the past or about conversational turns

    oai_token-act-pair · gemini-2.0-flash

    Past tense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     recent
    -0.88
    Recent
    -0.78
    recent
    -0.77
     recently
    -0.73
     Recent
    -0.70
    recently
    -0.70
     RECENT
    -0.68
     reciente
    -0.66
    Recently
    -0.65
     recente
    -0.65
    POSITIVE LOGITS
    setVerticalGroup
    0.96
     Administrativna
    0.93
    AddTagHelper
    0.90
     nonUne
    0.87
    цездатний
    0.86
    клопе
    0.83
     >=",
    0.79
     通販
    0.78
    CppMethod
    0.78
    ]")]
    0.77
    Activations Density 2.514%

    No Known Activations