© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14290
    Prev
    Next
    INDEX
    Explanations

    instances of verbs used in the context of goals or processes

    oai_token-act-pair · gemini-2.0-flash

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     find
    -1.02
    find
    -0.98
    Find
    -0.90
     Find
    -0.90
     finds
    -0.84
     FIND
    -0.82
     finding
    -0.81
    finding
    -0.75
     encontrar
    -0.75
    FIND
    -0.73
    POSITIVE LOGITS
    expandindo
    0.94
     Efq
    0.90
     Monfieur
    0.84
     purpoſe
    0.84
    __((
    0.83
    AnchorStyles
    0.81
    المناصب
    0.80
     Roskov
    0.80
     Theſe
    0.77
    RegressionTest
    0.75
    Activations Density 15.503%

    No Known Activations