© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12010
    Prev
    Next
    INDEX
    Explanations

    latin prefixes and suffixes

    oai_token-act-pair · gemini-2.0-flash

    prefixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    enumi
    -0.83
     AssemblyCulture
    -0.79
     doInBackground
    -0.74
     EconPapers
    -0.67
    +#+#
    -0.67
     TÉCN
    -0.66
     Theſe
    -0.66
     Monfieur
    -0.66
     Inscrivez
    -0.65
     Amiens
    -0.64
    POSITIVE LOGITS
    tagext
    0.53
    Билгалдахарш
    0.52
    %</
    0.52
    Identyfik
    0.51
    ActionMode
    0.49
    {}'.
    0.48
    rungsseite
    0.47
    styleUrls
    0.47
    ')):
    0.47
    <bos>
    0.45
    Activations Density 0.489%

    No Known Activations