© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1162
    Prev
    Next
    INDEX
    Explanations

    code and programming instructions, but also seems to be sensitive to locations(in, on) and a few descriptive(large, whole) words

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    getWriter
    -0.53
    awtextra
    -0.52
    sak
    -0.52
    DebuggerStep
    -0.51
    +#+#
    -0.48
    createStatement
    -0.47
    stdafx
    -0.47
     Wikimedijinoj
    -0.46
    TestingModule
    -0.46
    +][
    -0.45
    POSITIVE LOGITS
    TagMode
    0.58
    MLLoader
    0.58
    Portale
    0.56
     Exactos
    0.54
     mules
    0.51
     Superhost
    0.51
    lining
    0.50
     photolibrary
    0.50
    لينكات
    0.50
    TableHead
    0.50
    Activations Density 8.825%

    No Known Activations