© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7457
    Prev
    Next
    INDEX
    Explanations

    words ending in "ies", "ie", "ty", "ers", "stops", or containing the letter "V"

    oai_token-act-pair · gemini-2.0-flash

    ie

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ГЛА
    -0.54
    pta
    -0.48
     CHAIN
    -0.46
    CHAIN
    -0.46
    nextLine
    -0.43
    ाष
    -0.43
    naver
    -0.43
     EventArgs
    -0.43
    Chain
    -0.42
     AssemblyVersion
    -0.42
    POSITIVE LOGITS
     Meksiku
    0.87
     Efq
    0.79
     Monfieur
    0.76
     myſelf
    0.75
    bootstrapcdn
    0.74
    ^(@)
    0.72
    ſelf
    0.71
    AccessorTable
    0.68
     muualla
    0.68
     houſe
    0.67
    Activations Density 0.644%

    No Known Activations