© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12578
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and adjectives followed by a noun, sometimes identifying the possessor

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AppCompatTheme
    -0.75
     doInBackground
    -0.62
     "..\..\
    -0.58
     الاطلاع
    -0.57
     AssemblyCulture
    -0.56
     digne
    -0.56
     Gorb
    -0.54
     Kraj
    -0.54
     Yours
    -0.54
    ndice
    -0.53
    POSITIVE LOGITS
    <bos>
    1.84
    StructEnd
    0.50
    FundMe
    0.49
    ImageField
    0.48
    PreAuthorize
    0.47
    WebServlet
    0.46
    PostExecute
    0.45
    saraba
    0.45
     B
    0.44
    PreExecute
    0.44
    Activations Density 0.931%

    No Known Activations