© 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. 4285
    Prev
    Next
    INDEX
    Explanations

    copyright notices in code

    oai_token-act-pair · gemini-2.0-flash

    copyright

    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
     di
    -0.63
     to
    -0.62
    epam
    -0.56
     v
    -0.55
     '
    -0.54
    .
    -0.54
     on
    -0.53
     \
    -0.52
     with
    -0.52
     a
    -0.51
    POSITIVE LOGITS
     itſelf
    1.22
     Jefus
    1.21
     raiſ
    1.14
     Efq
    1.12
     myſelf
    1.12
     becauſe
    1.11
    rungsseite
    1.08
     Chrift
    1.07
     himſelf
    1.06
     neceff
    1.06
    Activations Density 0.785%

    No Known Activations