© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6142
    Prev
    Next
    INDEX
    Explanations

    words related to adherence in technical documents, particularly those including the "adhere" prefix or suffix "lage".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mxArray
    -0.75
    Personendaten
    -0.69
    IsMutable
    -0.68
     متعلقه
    -0.65
     Савезне
    -0.65
    eterangan
    -0.64
     المعيارى
    -0.62
    MessageOf
    -0.61
     Vane
    -0.60
    migrationBuilder
    -0.58
    POSITIVE LOGITS
     clinging
    0.88
     clung
    0.85
     cling
    0.84
     clings
    0.82
     adher
    0.80
    attach
    0.78
     attachment
    0.77
     attached
    0.75
     attachments
    0.73
     attach
    0.72
    Activations Density 0.694%

    No Known Activations