© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12315
    Prev
    Next
    INDEX
    Explanations

    CSS styling attributes such as position, alignment, and size

    oai_token-act-pair · gemini-2.0-flash

    center

    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
     Majefty
    -0.76
    FTFY
    -0.73
     Mémoires
    -0.72
     Daß
    -0.67
     raiſ
    -0.67
     RouterModule
    -0.66
    jalá
    -0.66
     Efq
    -0.65
     faſt
    -0.64
     pleaſure
    -0.64
    POSITIVE LOGITS
    __':
    0.45
    fjspx
    0.45
    Indented
    0.43
    BeginContext
    0.42
    urban
    0.41
    ◄
    0.40
    ran
    0.40
    çage
    0.40
     Pardo
    0.39
    רד
    0.38
    Activations Density 0.511%

    No Known Activations