© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 1012
    Prev
    Next
    INDEX
    Explanations

    references to methodologies and how things work

    oai_token-act-pair · gemini-2.0-flash

    which would

    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
     how
    -1.27
     कैसे
    -1.24
    איך
    -1.11
     איך
    -1.05
     چگونه
    -1.02
     cómo
    -1.01
    Hogyan
    -1.01
    how
    -1.00
    cómo
    -1.00
     manner
    -0.97
    POSITIVE LOGITS
     sporo
    0.48
     existência
    0.46
     Datenbank
    0.45
     fly
    0.43
     tenham
    0.42
     nuvem
    0.42
    IMPORTED
    0.42
     cite
    0.41
    Bson
    0.41
     vouloir
    0.41
    Activations Density 1.647%

    No Known Activations