© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11552
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "is" followed by an adjective

    oai_token-act-pair · gemini-2.0-flash

    Appropriateness or Reccomendation

    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
     completeness
    -0.60
    sprogramm
    -0.58
    __':
    -0.57
     Chalmers
    -0.55
    sproble
    -0.54
    __":
    -0.54
     bordes
    -0.53
     vuitton
    -0.52
    fficio
    -0.52
    ubility
    -0.51
    POSITIVE LOGITS
    webElementXpaths
    0.71
     propOrder
    0.68
    GraphicsUnit
    0.65
    tagHelperRunner
    0.60
    RegistryLite
    0.58
    MigrationBuilder
    0.57
     passphrase
    0.54
    WebControls
    0.54
    évaluateur
    0.54
    fjspx
    0.52
    Activations Density 1.681%

    No Known Activations