© 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. 7483
    Prev
    Next
    INDEX
    Explanations

    instances of the letters 'Gr' together, often as part of a name

    oai_token-act-pair · gemini-2.0-flash

    Gr and Br

    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
    able
    -0.68
    ed
    -0.64
     Савезне
    -0.59
    ValueStyle
    -0.58
    a
    -0.56
    ama
    -0.52
    ai
    -0.51
    ا
    -0.50
    o
    -0.50
    DebuggerNonUser
    -0.50
    POSITIVE LOGITS
    UCE
    0.53
    ULER
    0.45
    IZ
    0.45
    Appearances
    0.44
    bula
    0.44
     Egl
    0.44
    ngrx
    0.43
    IZE
    0.43
    IZEN
    0.43
    ucing
    0.41
    Activations Density 3.544%

    No Known Activations