© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 398
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    equations and formulas

    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
    BeginContext
    -0.64
     MainAxisSize
    -0.58
    nologue
    -0.54
    Geplaatst
    -0.51
    الدراسه
    -0.50
    GraphicsUnit
    -0.50
     يتيمه
    -0.50
    Advertise
    -0.49
    клопе
    -0.49
    aarrggbb
    -0.48
    POSITIVE LOGITS
    AccessorTable
    0.65
    nT
    0.62
    mY
    0.59
    nq
    0.58
    nM
    0.57
    mj
    0.57
    mView
    0.57
    nk
    0.57
    mId
    0.56
    mText
    0.56
    Activations Density 17.635%

    No Known Activations