© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3650
    Prev
    Next
    INDEX
    Explanations

    the word "interest," sometimes in the financial sense, sometimes referring to a quality of a thing

    oai_token-act-pair · gemini-2.0-flash

    interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     interest
    -2.92
     Interest
    -2.56
    interest
    -2.45
    Interest
    -2.44
     interests
    -2.28
     INTEREST
    -2.17
    INTEREST
    -2.03
     Interests
    -1.98
    interests
    -1.90
     interés
    -1.79
    POSITIVE LOGITS
    }],
    0.75
     lenker
    0.66
    })));
    0.65
    </thead>
    0.63
     initComponents
    0.60
    numerusform
    0.60
    getExternal
    0.60
     contextLoads
    0.59
    }]
    0.59
    forKey
    0.59
    Activations Density 6.140%

    No Known Activations