© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14387
    Prev
    Next
    INDEX
    Explanations

    words indicating granduer or impressiveness, like "imposing".

    oai_token-act-pair · gemini-2.0-flash

    high quality description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    CodeAnalysis
    -0.44
     sting
    -0.41
     deuter
    -0.39
     tapes
    -0.38
    string
    -0.38
    ニュ
    -0.36
    ηγ
    -0.36
     CSA
    -0.36
     labios
    -0.36
     STRE
    -0.36
    POSITIVE LOGITS
    DockStyle
    1.37
    BeginContext
    1.05
     propOrder
    1.01
     typelib
    0.99
     كومونز
    0.90
    ificent
    0.89
     hObject
    0.89
     disponibilités
    0.88
    RenderAtEndOf
    0.88
    CloseOperation
    0.87
    Activations Density 1.170%

    No Known Activations