© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9647
    Prev
    Next
    INDEX
    Explanations

    general conversational language

    oai_token-act-pair · gemini-2.0-flash

    disappointment criticism

    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
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.60
    tilla
    -0.50
     AssemblyProduct
    -0.49
    끗
    -0.47
     unsuccessfully
    -0.46
     dovrebbe
    -0.44
    hetically
    -0.43
    öne
    -0.43
    XSSF
    -0.43
     edit
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.76
    uxxxx
    0.65
    __*/
    0.64
    mphony
    0.63
    StoryboardSegue
    0.61
     doInBackground
    0.59
    gott
    0.55
    SizeMode
    0.55
    kháu
    0.55
    पया
    0.55
    Activations Density 4.228%

    No Known Activations