© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13838
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs "be", "is", "are", "was", "were" and related words or phrases

    oai_token-act-pair · gemini-2.0-flash

    past participles related to actions

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

    Actions being performed

    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
     blive
    -0.52
     überlegen
    -0.47
    companying
    -0.46
     élas
    -0.45
     bambino
    -0.43
     compagn
    -0.43
    mentare
    -0.42
     kurios
    -0.42
     Begründung
    -0.41
     alvor
    -0.41
    POSITIVE LOGITS
     performed
    1.17
     played
    1.10
     brewed
    1.07
     executed
    1.05
     handled
    1.04
     conducted
    1.04
     bought
    1.02
     delivered
    1.02
     produced
    1.01
     accessed
    1.01
    Activations Density 3.220%

    No Known Activations