© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7734
    Prev
    Next
    INDEX
    Explanations

    references to television programs or episodes

    oai_token-act-pair · gemini-2.0-flash

    episode

    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
     episode
    -2.34
    Episode
    -1.99
    episode
    -1.98
     Episode
    -1.95
     episodes
    -1.95
     episódio
    -1.70
     episodio
    -1.63
     Episodes
    -1.63
     EPISODE
    -1.59
     épisode
    -1.57
    POSITIVE LOGITS
    werke
    0.59
    TargetException
    0.58
    EMPO
    0.56
    ruptedException
    0.56
    เตอร์
    0.54
    WEBPACK
    0.54
     Ago
    0.54
    hebt
    0.54
    terly
    0.53
     utafitiHapana
    0.53
    Activations Density 0.684%

    No Known Activations