© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words ending in "s" that could be possessive or plural

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pinulongan
    -0.92
     kasarigan
    -0.90
     виправивши
    -0.82
    corazón
    -0.81
    DockStyle
    -0.81
     Efq
    -0.76
     themſelves
    -0.71
     stället
    -0.68
    CppMethod
    -0.67
    AndroidJUnit
    -0.67
    POSITIVE LOGITS
    googleapis
    0.62
     z
    0.53
     ser
    0.50
     po
    0.49
    nEnter
    0.48
     pat
    0.47
    COLN
    0.47
     Katz
    0.45
     im
    0.45
     ze
    0.45
    Activations Density 1.197%

    No Known Activations