© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1920
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns, descriptive words, and verbs

    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_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Sign
    -0.52
    Sign
    -0.47
     sign
    -0.44
     prépar
    -0.41
    maat
    -0.40
    gorod
    -0.40
    pras
    -0.39
    žin
    -0.39
    urma
    -0.39
    omod
    -0.38
    POSITIVE LOGITS
    MigrationBuilder
    0.98
     AssemblyVersion
    0.92
    AddTagHelper
    0.86
     BoxFit
    0.84
    دانشنامهٔ
    0.82
    migrationBuilder
    0.82
    Jereo
    0.81
    Geplaatst
    0.81
    URLException
    0.80
    ագրություններ
    0.80
    Activations Density 13.882%

    No Known Activations