© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12117
    Prev
    Next
    INDEX
    Explanations

    references to actions that people can take or have taken.

    oai_token-act-pair · gemini-2.0-flash

    his, himself

    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
     herself
    -1.31
    herself
    -1.04
     itself
    -1.01
     themselves
    -0.95
    itself
    -0.95
     ihrer
    -0.87
     they
    -0.87
     elle
    -0.86
    她們
    -0.86
     نفسها
    -0.85
    POSITIVE LOGITS
     his
    2.16
    his
    1.63
     himself
    1.47
    彼の
    1.36
     he
    1.30
    彼は
    1.30
    他的
    1.30
    himself
    1.20
     그의
    1.20
    了他的
    1.16
    Activations Density 3.427%

    No Known Activations