© 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. 1462
    Prev
    Next
    INDEX
    Explanations

    positive evaluations of something, often using "useful"

    oai_token-act-pair · gemini-2.0-flash

    useful

    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
     useful
    -2.02
    useful
    -1.82
     Useful
    -1.73
     helpful
    -1.70
    Useful
    -1.62
    helpful
    -1.43
     Helpful
    -1.35
     utile
    -1.34
     útil
    -1.30
    Helpful
    -1.27
    POSITIVE LOGITS
    })`
    0.70
     الحره
    0.59
     AttributeSet
    0.54
     Compromise
    0.52
    LookAnd
    0.52
     jScrollPane
    0.52
    >(_
    0.52
    държа
    0.50
     estoque
    0.50
     بدان
    0.49
    Activations Density 8.750%

    No Known Activations