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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12552
    Prev
    Next
    INDEX
    Explanations

    a variety of things in different languages, including the letter 'a' and the word 'Bora'.

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     lenker
    -0.72
    دانشنامهٔ
    -0.58
     चीज़ों
    -0.58
     Burnett
    -0.54
     balade
    -0.53
    èlement
    -0.53
    atem
    -0.52
    راسیون
    -0.52
    vedať
    -0.51
     flexibles
    -0.51
    POSITIVE LOGITS
    GNA
    0.65
    #+#
    0.62
     của
    0.62
    ของ
    0.61
     المعيارى
    0.58
    0.57
     InkWell
    0.56
    躇
    0.55
    MockMvc
    0.55
    piecze
    0.55
    Activations Density 0.615%

    No Known Activations