© 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. 12289
    Prev
    Next
    INDEX
    Explanations

    code and markup syntax

    oai_token-act-pair · gemini-2.0-flash

    code/API

    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
    yethyl
    -0.40
    нен
    -0.40
     cá
    -0.38
    xFFFFFF
    -0.38
    umo
    -0.37
    вен
    -0.37
    éo
    -0.36
    ref
    -0.36
    kop
    -0.36
    MathML
    -0.36
    POSITIVE LOGITS
    ⓧ
    0.48
     Efq
    0.43
     ſeveral
    0.40
    Personendaten
    0.40
     Majefty
    0.40
     ویکی‌پدی
    0.40
     Theſe
    0.38
     Roskov
    0.38
     themſelves
    0.38
     ویکی‌پدیا
    0.38
    Activations Density 0.406%

    No Known Activations