© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13523
    Prev
    Next
    INDEX
    Explanations

    references to people and possession

    oai_token-act-pair · gemini-2.0-flash

    He/She

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     -
    -0.56
    :
    -0.48
     
    -0.45
     have
    -0.44
     –
    -0.43
    have
    -0.43
    .
    -0.43
     on
    -0.42
     in
    -0.41
    ↵↵
    -0.41
    POSITIVE LOGITS
     learns
    1.27
     Efq
    1.27
     wears
    1.25
     knows
    1.24
     realizes
    1.18
    ValueStyle
    1.18
     propOrder
    1.18
     sees
    1.17
    knows
    1.17
     chooses
    1.15
    Activations Density 7.797%

    No Known Activations