© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7910
    Prev
    Next
    INDEX
    Explanations

    occurrences of functional words (like "the" and "of") and verbs (like "were") alongside subject-matter words (like "bones" and "women")

    oai_token-act-pair · gemini-2.0-flash

    impact

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ligiloj
    -0.61
    oflu
    -0.52
     esternos
    -0.52
     rí
    -0.51
     bezeichneter
    -0.50
    Closeable
    -0.48
    onomía
    -0.48
    rungsseite
    -0.46
     disambiguazione
    -0.46
     cherchés
    -0.46
    POSITIVE LOGITS
     impact
    1.56
    impact
    1.32
     impacts
    1.30
    Impact
    1.20
     Impact
    1.16
     IMPACT
    1.15
    IMPACT
    1.09
    Impacts
    1.00
     impacting
    1.00
     impacto
    1.00
    Activations Density 11.054%

    No Known Activations