© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12008
    Prev
    Next
    INDEX
    Explanations

    code syntax

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    AddTagHelper
    -0.47
    strona
    -0.46
    ANTY
    -0.45
    كويكب
    -0.44
    transQ
    -0.43
     alt
    -0.43
    rouvez
    -0.42
    ,
    -0.41
    elesaikan
    -0.41
    alto
    -0.41
    POSITIVE LOGITS
     Shakspeare
    0.83
    पया
    0.72
    TestBed
    0.68
     Shaksp
    0.67
     pinulongan
    0.66
    RenderAtEndOf
    0.65
    WebMethod
    0.65
     Aphrodite
    0.65
     CPF
    0.63
     Thebes
    0.63
    Activations Density 2.515%

    No Known Activations