© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4318
    Prev
    Next
    INDEX
    Explanations

    C or C++ code.

    oai_token-act-pair · gemini-2.0-flash

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    endphp
    -0.53
    WriteLiteral
    -0.53
    ]+=
    -0.52
    endforeach
    -0.51
    andExpect
    -0.47
    rab
    -0.45
     mã
    -0.43
    CodedInputStream
    -0.42
     금
    -0.41
    NameInMap
    -0.41
    POSITIVE LOGITS
     فريبيس
    0.68
    :+:
    0.66
    ,‎
    0.63
    AsUp
    0.62
    nalités
    0.60
     GoogleFonts
    0.57
    UPAC
    0.56
     للمعارف
    0.56
    AxisAlignment
    0.54
     Wiktionnaire
    0.54
    Activations Density 1.805%

    No Known Activations