© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6562
    Prev
    Next
    INDEX
    Explanations

    technical explanations, questions, and possible solutions to problems in a variety of fields.

    oai_token-act-pair · gemini-2.0-flash

    various forms of the verb "work"

    np_token-act-pair-logits · gpt-4o-mini

    working

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    UnknownFieldSet
    -0.47
     consultato
    -0.42
    mybatisplus
    -0.42
    PutMapping
    -0.41
    Спасылкі
    -0.40
    borderFill
    -0.39
    TestRunner
    -0.39
     NSCoder
    -0.39
    alleros
    -0.38
    vnd
    -0.37
    POSITIVE LOGITS
     working
    3.41
    working
    3.05
     Working
    2.92
    Working
    2.92
     WORKING
    2.86
    WORKING
    2.70
     worked
    2.19
     works
    2.00
     trabajando
    1.96
    worked
    1.89
    Activations Density 3.669%

    No Known Activations