© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4404
    Prev
    Next
    INDEX
    Explanations

    phrases expressing an intention or need to do something

    oai_token-act-pair · gemini-2.0-flash

    variations of the verb "keep"

    np_token-act-pair-logits · gpt-4o-mini

    keep

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ंदीखरीदारी
    -0.85
     Roskov
    -0.71
     ويكيپيديا
    -0.70
    RenderAtEndOf
    -0.70
     nahilalakip
    -0.70
    ArrowToggle
    -0.68
     IndexPath
    -0.67
    /**
    -0.66
     SqlDbType
    -0.65
    Diwedd
    -0.65
    POSITIVE LOGITS
     keep
    1.42
     kept
    1.37
     keeps
    1.34
     Keep
    1.33
    Keep
    1.30
     keeping
    1.30
    keep
    1.24
     Keeping
    1.23
    Keeping
    1.23
     KEEP
    1.20
    Activations Density 2.325%

    No Known Activations