© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7087
    Prev
    Next
    INDEX
    Explanations

    words in a variety of languages and contexts that are not obviously related, but all have the ending "-ity".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     nguồn
    -0.54
    τως
    -0.48
     volon
    -0.47
     Bue
    -0.46
    strahlung
    -0.45
     gospod
    -0.45
     öne
    -0.45
    考验
    -0.45
    生效
    -0.44
     térm
    -0.43
    POSITIVE LOGITS
     they
    0.99
     we
    0.97
     she
    0.91
     he
    0.90
    ValueStyle
    0.85
    they
    0.84
     We
    0.80
    We
    0.80
    she
    0.79
     ſhe
    0.79
    Activations Density 24.017%

    No Known Activations