© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5584
    Prev
    Next
    INDEX
    Explanations

    the words 'short', 'long', 'term' and 'round'.

    oai_token-act-pair · gemini-2.0-flash

    short

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     Monfieur
    -0.68
     reaſon
    -0.64
     itſelf
    -0.59
    ſelf
    -0.59
     whoſe
    -0.59
     محفوظة
    -0.58
     الحره
    -0.57
     masculinos
    -0.57
     auffi
    -0.57
     myſelf
    -0.56
    POSITIVE LOGITS
    ագրություններ
    0.58
    PhysRev
    0.54
    참고
    0.49
    PrintWriter
    0.45
    чется
    0.44
    lah
    0.44
     pro
    0.43
     against
    0.43
    CURLOPT
    0.42
    ensively
    0.42
    Activations Density 2.459%

    No Known Activations