© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11608
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns.

    oai_token-act-pair · gemini-2.0-flash

    My

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     humaines
    -0.58
     umane
    -0.56
     arrivato
    -0.52
    hésite
    -0.50
     umana
    -0.49
     nostru
    -0.49
     vectorielles
    -0.49
     venuto
    -0.47
     meille
    -0.47
     koska
    -0.47
    POSITIVE LOGITS
    __":
    0.81
    __":
    0.78
     насеље
    0.76
    __':
    0.75
     favorite
    0.73
    __':
    0.72
    aspectj
    0.67
    Становништво
    0.66
     vision
    0.65
    期刊论文
    0.64
    Activations Density 4.174%

    No Known Activations