© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4008
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and certain variables

    oai_token-act-pair · gemini-2.0-flash

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.76
    ↵
    -1.49
    <eos>
    -1.46
     (
    -1.46
    ↵↵
    -1.39
     L
    -1.38
     I
    -1.37
    .
    -1.35
     B
    -1.33
     the
    -1.32
    POSITIVE LOGITS
     myſelf
    3.44
     Efq
    3.36
     itſelf
    3.27
     Monfieur
    3.16
     pleaſure
    3.11
     Majefty
    3.06
     themſelves
    3.03
     purpoſe
    3.02
     Houſe
    3.00
     raiſ
    2.95
    Activations Density 1.852%

    No Known Activations