© 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. 15355
    Prev
    Next
    INDEX
    Explanations

    things enclosed in square brackets and surrounded by asterisks

    oai_token-act-pair · gemini-2.0-flash

    **

    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
     OMITBAD
    -0.66
    ModelBuilder
    -0.52
    haben
    -0.49
    minecraftforge
    -0.48
    الحياه
    -0.45
     noDo
    -0.44
    pac
    -0.44
    unsch
    -0.44
    aarrggbb
    -0.43
     захо
    -0.43
    POSITIVE LOGITS
    InSection
    0.60
    resaid
    0.59
    ]<<"
    0.57
     Efq
    0.56
     leaſt
    0.54
     myſelf
    0.53
    脚注の使い方
    0.53
    новништво
    0.53
     بيها
    0.52
    outSlope
    0.52
    Activations Density 0.083%

    No Known Activations