© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12510
    Prev
    Next
    INDEX
    Explanations

    the word "first," along with words related to groups or clubs

    oai_token-act-pair · gemini-2.0-flash

    first

    np_max-act · gemini-2.0-flash

    first Method used: 1 — reason: MAX_ACTIVATING_TOKENS identical — explanation: first

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     XNUMX
    -0.78
    NUMX
    -0.78
     arşivlendi
    -0.69
    󠁴
    -0.68
    kloped
    -0.66
    Closer
    -0.65
    interopRequire
    -0.65
     IDisposable
    -0.64
    âce
    -0.63
    featureID
    -0.63
    POSITIVE LOGITS
    <bos>
    1.60
     the
    0.77
      
    0.57
     illetve
    0.53
    ’
    0.52
     nakalista
    0.52
     ahogy
    0.52
    Model
    0.50
     hiszen
    0.50
     dagens
    0.49
    Activations Density 2.012%

    No Known Activations