© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7211
    Prev
    Next
    INDEX
    Explanations

    words that could precede or follow prepositions, as well as words related to supporting a claim or making an argument.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    In
    -0.57
    On
    -0.57
    Its
    -0.56
    from
    -0.56
     pauvres
    -0.53
    At
    -0.51
    Their
    -0.50
    MLLoader
    -0.50
    upon
    -0.49
     In
    -0.48
    POSITIVE LOGITS
    -
    0.93
     CURIAM
    0.67
    Merkmale
    0.64
    RetentionPolicy
    0.61
    -​
    0.59
     كومونز
    0.58
    ](#
    0.57
     MERCHANTABILITY
    0.57
    WebElementEntity
    0.56
     Melrose
    0.56
    Activations Density 18.864%

    No Known Activations