© 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. 11228
    Prev
    Next
    INDEX
    Explanations

    words related to needs of people and how to fulfill them, especially in leadership or service contexts.

    oai_token-act-pair · gemini-2.0-flash

    needs

    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
    IntoConstraints
    -0.80
     needs
    -0.75
     Needs
    -0.73
    WithIOException
    -0.66
     igény
    -0.65
    needs
    -0.65
     Bedürf
    -0.64
     NEEDS
    -0.64
     kebutuhan
    -0.63
     blessés
    -0.63
    POSITIVE LOGITS
    edipus
    0.45
    <bos>
    0.40
    Заключение
    0.38
    InputBorder
    0.36
    }];
    0.36
    curkan
    0.36
     שב
    0.36
     الحره
    0.36
    Personensuche
    0.36
    mission
    0.35
    Activations Density 16.587%

    No Known Activations