© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7249
    Prev
    Next
    INDEX
    Explanations

    identifiers such as serial numbers and codes

    oai_token-act-pair · gemini-2.0-flash

    dash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    1
    -1.31
    0
    -1.30
    2
    -0.92
    ０
    -0.75
    3
    -0.73
    ০
    -0.67
    １
    -0.65
    IsContent
    -0.65
     '\\;'
    -0.61
    𝟎
    -0.60
    POSITIVE LOGITS
    TestingModule
    0.52
    ⁸
    0.47
    :^{
    0.47
    +");
    0.44
     שוליים
    0.43
    mologie
    0.42
    ագրություններ
    0.41
    
    0.41
    ⁹
    0.41
     locu
    0.40
    Activations Density 7.240%

    No Known Activations