© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12478
    Prev
    Next
    INDEX
    Explanations

    references to people, including personal pronouns, especially in questions or requests

    oai_token-act-pair · gemini-2.0-flash

    someone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    )];
    -0.81
    TintMode
    -0.73
    хьтан
    -0.72
    =$?
    -0.71
    resave
    -0.71
    delwed
    -0.70
    verwijspagina
    -0.68
     otomatig
    -0.68
    StructEnd
    -0.67
    دانشنامهٔ
    -0.67
    POSITIVE LOGITS
    '
    0.55
    niejsza
    0.52
     who
    0.48
     on
    0.48
    ’
    0.47
     quelles
    0.45
    essentiel
    0.44
    #+#
    0.44
     with
    0.43
     aans
    0.43
    Activations Density 3.222%

    No Known Activations