© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15469
    Prev
    Next
    INDEX
    Explanations

    phrases followed by the word "problems" or relating to scholarly publications in biology

    oai_token-act-pair · gemini-2.0-flash

    problems, death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ponses
    -0.71
     كومونز
    -0.62
    出版年
    -0.61
    ngdoc
    -0.61
     cipolla
    -0.59
     immemorial
    -0.56
    +#+#
    -0.54
    AddHtmlAttribute
    -0.54
    UserScript
    -0.54
    </tfoot>
    -0.53
    POSITIVE LOGITS
     nahilalakip
    0.59
     getopt
    0.50
    MessageTagHelper
    0.50
     suk
    0.49
    "]];
    0.49
     dried
    0.46
    _
    0.45
    `,
    0.45
     houſe
    0.44
     ]
    0.44
    Activations Density 0.355%

    No Known Activations