© 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. 14375
    Prev
    Next
    INDEX
    Explanations

    the substring 'mk'

    oai_token-act-pair · gemini-2.0-flash

    Code/programming snippets

    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
     سكانية
    -0.75
     يتيمه
    -0.72
     AssemblyTitle
    -0.68
    thâu
    -0.64
     ModelExpression
    -0.59
    AndroidJUnit
    -0.59
    tanooga
    -0.58
     linkovi
    -0.58
    skosten
    -0.58
    NewGuid
    -0.57
    POSITIVE LOGITS
     may
    0.56
     inaweza
    0.53
    may
    0.51
    ="_
    0.49
     ويكيميديا
    0.47
     सकते
    0.45
    \}=\
    0.45
    EMOS
    0.45
     peut
    0.44
     mời
    0.43
    Activations Density 0.140%

    No Known Activations