© 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. 10781
    Prev
    Next
    INDEX
    Explanations

    the word "at" that preceeds a legal "issue" or "stake"

    oai_token-act-pair · gemini-2.0-flash

    at

    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
    ThroughAttribute
    -0.77
    TypedDataSet
    -0.73
     فريبيس
    -0.69
    MergeFrom
    -0.68
    mybatisplus
    -0.66
     useDispatch
    -0.66
    ❉
    -0.62
     محفوظة
    -0.60
    Xna
    -0.59
    .*")]
    -0.59
    POSITIVE LOGITS
     war
    0.52
    man
    0.51
    都知道
    0.42
    fiets
    0.41
    Clyde
    0.40
    manship
    0.39
    IFA
    0.39
    ̣c
    0.39
    ITUTION
    0.39
     hand
    0.39
    Activations Density 1.034%

    No Known Activations