© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10558
    Prev
    Next
    INDEX
    Explanations

    the word "arm" and related parts of a programming language (arguments, arrays, etc.)

    oai_token-act-pair · gemini-2.0-flash

    Coding and programming related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    bakar
    -0.60
    criminator
    -0.58
    igshid
    -0.58
    اعمال
    -0.54
     Trimble
    -0.54
    󠁢
    -0.53
    URBANA
    -0.53
     inapropiados
    -0.52
    authorize
    -0.49
    cdef
    -0.48
    POSITIVE LOGITS
    новниш
    0.65
    __':
    0.57
    ContentAsync
    0.55
    Personendaten
    0.54
    __":
    0.54
     الحره
    0.53
     مشين
    0.53
    ÈRE
    0.52
    eed
    0.51
     --;
    0.51
    Activations Density 4.354%

    No Known Activations