© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13258
    Prev
    Next
    INDEX
    Explanations

    references to Facebook pages including URLs

    oai_token-act-pair · gemini-2.0-flash

    facebook

    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
    __':
    -0.46
    ricians
    -0.45
    __':
    -0.45
    وفاته
    -0.43
    Whew
    -0.42
    toHexString
    -0.41
    Phew
    -0.41
    ANTLR
    -0.41
    DockStyle
    -0.40
    enumi
    -0.40
    POSITIVE LOGITS
     Facebook
    0.86
     facebook
    0.83
     raiſ
    0.82
    Facebook
    0.80
     فريبيس
    0.75
     FACEBOOK
    0.75
     itſelf
    0.74
     tranſ
    0.72
     juſt
    0.71
     faſt
    0.69
    Activations Density 0.388%

    No Known Activations