© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11056
    Prev
    Next
    INDEX
    Explanations

    words that are formed by adding suffixes, particularly "en", "ed", and "ves"

    oai_token-act-pair · gemini-2.0-flash

    obligation/recommendation

    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
    httphttps
    -0.76
    Portály
    -0.64
    principalColumn
    -0.63
    міністра
    -0.57
    RunAsync
    -0.57
     snippetHide
    -0.52
    ModelAdmin
    -0.52
    Lähteet
    -0.52
    djangoproject
    -0.52
    multicolumn
    -0.52
    POSITIVE LOGITS
     before
    0.71
    Between
    0.67
     Before
    0.66
    Before
    0.66
     BEFORE
    0.65
     BETWEEN
    0.65
    before
    0.61
    Sebelum
    0.60
     Between
    0.59
     between
    0.59
    Activations Density 0.302%

    No Known Activations