© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3252
    Prev
    Next
    INDEX
    Explanations

    mentions of errors

    oai_token-act-pair · gemini-2.0-flash

    error

    np_max-act · gemini-2.0-flash

    error

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     Theſe
    -0.88
     Anſ
    -0.81
     Conſ
    -0.80
     ―――――
    -0.80
     faſt
    -0.78
     Inſ
    -0.75
     myſelf
    -0.74
     Houſe
    -0.73
     ――――
    -0.72
     Diſ
    -0.67
    POSITIVE LOGITS
     CreateTagHelper
    1.11
    +#+
    1.05
    RegressionTest
    1.04
    ArgsConstructor
    1.01
     commerciaux
    0.94
    нгред
    0.94
    IsMutable
    0.94
    WebVitals
    0.93
     Réponses
    0.91
     commerciales
    0.91
    Activations Density 2.871%

    No Known Activations