© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    the word "length" and words related to measurement

    oai_token-act-pair · gemini-2.0-flash

    length

    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
     length
    -2.84
     Length
    -2.55
    length
    -2.48
    Length
    -2.47
     LENGTH
    -2.27
     lengths
    -2.20
    LENGTH
    -1.98
     lenght
    -1.97
    长度
    -1.77
     longueur
    -1.72
    POSITIVE LOGITS
    modb
    0.61
    OrNil
    0.52
    aluz
    0.52
    webElementGuid
    0.51
     &___
    0.50
    numerus
    0.49
    MLLoader
    0.49
     pareti
    0.49
    migrationBuilder
    0.48
    IntoConstraints
    0.48
    Activations Density 0.598%

    No Known Activations