© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12600
    Prev
    Next
    INDEX
    Explanations

    text from a discussion about flagging content for moderation

    oai_token-act-pair · gemini-2.0-flash

    issue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    HasForeignKey
    -0.59
     '\\;'
    -0.51
    \
    -0.50
     مرئيه
    -0.49
    inheritDoc
    -0.49
     issus
    -0.49
    lsa
    -0.47
    ⓧ
    -0.47
    processData
    -0.47
     him
    -0.47
    POSITIVE LOGITS
    kháu
    0.60
    amssymb
    0.60
    elemField
    0.56
     AspNetCore
    0.55
     bpy
    0.54
    onames
    0.52
     Monks
    0.52
    atoday
    0.52
    nemers
    0.50
    ContentLoaded
    0.50
    Activations Density 5.957%

    No Known Activations