© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3965
    Prev
    Next
    INDEX
    Explanations

    descriptive and superlative adverbs and adjectives

    oai_token-act-pair · gemini-2.0-flash

    Closing punctuation

    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
    Negative Logits
     مشين
    -1.02
     NSCoder
    -0.96
     ostavi
    -0.94
    findpost
    -0.90
    ImageContext
    -0.89
     bezeichneter
    -0.87
    StoryboardSegue
    -0.86
    NewUrlParser
    -0.86
     tartalomajánló
    -0.85
     utafitiHapana
    -0.84
    POSITIVE LOGITS
    ]
    0.69
    )
    0.65
    ()
    0.57
    ;
    0.54
    "
    0.51
    }
    0.50
    che
    0.50
    </td>
    0.49
    </b>
    0.48
    </code>
    0.48
    Activations Density 27.276%

    No Known Activations