© 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. 3837
    Prev
    Next
    INDEX
    Explanations

    the word "in" when it's used as a preposition.

    oai_token-act-pair · gemini-2.0-flash

    gerunds related to actions

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

    in

    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
     nacionais
    -0.44
     sahiptir
    -0.42
     existência
    -0.42
     questão
    -0.42
     possibilidade
    -0.41
     necessidade
    -0.41
     suceder
    -0.41
    ască
    -0.41
     ocurrir
    -0.41
     braccio
    -0.41
    POSITIVE LOGITS
     delivering
    1.20
     respecting
    1.08
     bringing
    1.07
     promoting
    1.05
     helping
    1.04
     introducing
    1.04
     implementing
    1.02
     providing
    1.02
     addressing
    1.02
     showing
    1.02
    Activations Density 1.920%

    No Known Activations