© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13545
    Prev
    Next
    INDEX
    Explanations

    the word "episode" and similar words

    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_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
    Negative Logits
    <bos>
    -1.53
     mukana
    -0.91
    olesale
    -0.83
    pecially
    -0.82
    nicity
    -0.82
    NESDAY
    -0.80
    NUMX
    -0.77
    elfare
    -0.77
     beginnetje
    -0.76
     Monfieur
    -0.76
    POSITIVE LOGITS
    inal
    0.66
     abstra
    0.63
    </td>
    0.62
    ";
    0.61
    apor
    0.61
    ina
    0.60
    ma
    0.59
    int
    0.59
    lob
    0.59
    iste
    0.58
    Activations Density 1.739%

    No Known Activations