© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8701
    Prev
    Next
    INDEX
    Explanations

    technical documentation in the fields of mathematics, electrical engineering, and physics

    oai_token-act-pair · gemini-2.0-flash

    electrical engineering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    LookAnd
    -0.95
    +#+#
    -0.94
    AndEndTag
    -0.91
    tagHelperRunner
    -0.91
     esternos
    -0.90
     تضيفلها
    -0.89
     myſelf
    -0.86
     leaſt
    -0.84
     raiſ
    -0.82
     Efq
    -0.82
    POSITIVE LOGITS
     
    0.52
     O
    0.50
     or
    0.49
     o
    0.49
     <
    0.47
    anti
    0.46
    us
    0.46
     Mar
    0.45
     x
    0.45
    weg
    0.45
    Activations Density 5.842%

    No Known Activations