© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6343
    Prev
    Next
    INDEX
    Explanations

    the word 'also'

    oai_token-act-pair · gemini-2.0-flash

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Tikang
    -0.61
     nød
    -0.54
    ⓧ
    -0.54
    leyeb
    -0.51
     kılıf
    -0.51
    acaktır
    -0.51
    mobileqq
    -0.49
    ıyı
    -0.49
    labilir
    -0.45
    üyor
    -0.44
    POSITIVE LOGITS
    NOPQRST
    0.74
     AssemblyVersion
    0.72
    DrawerToggle
    0.68
     ComVisible
    0.63
    WebServlet
    0.63
    OwnProperty
    0.63
    UIControlState
    0.63
    imize
    0.62
    principalColumn
    0.60
    bcrypt
    0.59
    Activations Density 0.141%

    No Known Activations