© 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. 6615
    Prev
    Next
    INDEX
    Explanations

    acronyms, code, or numbers inside text

    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
    SharedDtor
    -1.20
     Monfieur
    -1.07
     Jefus
    -1.05
     pleaſure
    -1.04
     تضيفلها
    -1.02
     Efq
    -1.01
     chofe
    -0.97
     Anſ
    -0.96
    ^(@)
    -0.96
     againſt
    -0.94
    POSITIVE LOGITS
     she
    0.57
     des
    0.49
     civil
    0.48
     lo
    0.47
     une
    0.46
     un
    0.45
    she
    0.45
     he
    0.45
     e
    0.44
     ag
    0.42
    Activations Density 1.170%

    No Known Activations