© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    technical instructions

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
    oredCriteria
    -0.81
    afficheront
    -0.65
    transQ
    -0.64
     mostrarán
    -0.60
    انجليز
    -0.52
    resizingMask
    -0.52
    alami
    -0.52
     NUKAT
    -0.51
    TestBed
    -0.51
    newswire
    -0.49
    POSITIVE LOGITS
     preocupes
    0.56
    dafx
    0.54
     blest
    0.53
    ArgsConstructor
    0.51
     lolita
    0.49
    rxjs
    0.48
     Assy
    0.48
     aimé
    0.48
     belonged
    0.47
    Jereo
    0.47
    Activations Density 0.632%

    No Known Activations