© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15509
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions within technical writing

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     lãnh
    -0.56
    -0.49
     直
    -0.49
    直
    -0.48
     Pristupljeno
    -0.48
    otto
    -0.47
    βά
    -0.46
    ┗
    -0.45
     Gatt
    -0.45
    Meto
    -0.44
    POSITIVE LOGITS
    OGND
    0.78
     INTERESAR
    0.77
     noDo
    0.76
    ंदीखरीदारी
    0.73
    PerformLayout
    0.71
     gyhoeddwyd
    0.71
     виправивши
    0.68
    บุรี
    0.68
    <bos>
    0.66
     ProtoMessage
    0.66
    Activations Density 6.245%

    No Known Activations