© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9897
    Prev
    Next
    INDEX
    Explanations

    html form elements that include the word 'edit'

    oai_token-act-pair · gemini-2.0-flash

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     edit
    -2.42
     Edit
    -2.25
    edit
    -2.19
    Edit
    -2.19
     EDIT
    -1.90
     edited
    -1.84
     editing
    -1.84
     edits
    -1.73
     editor
    -1.73
    EDIT
    -1.73
    POSITIVE LOGITS
    audiovisuel
    0.64
    eradish
    0.52
    auce
    0.52
    êu
    0.50
    LIA
    0.49
    DAE
    0.49
    gique
    0.48
     turística
    0.48
    prefixer
    0.47
     PW
    0.46
    Activations Density 6.325%

    No Known Activations