© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5759
    Prev
    Next
    INDEX
    Explanations

    the word 'capability'.

    oai_token-act-pair · gemini-2.0-flash

    capability

    np_max-act · gemini-2.0-flash
    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
     ſche
    -0.94
     Diſ
    -0.94
     Houſe
    -0.90
     ſeveral
    -0.87
     pleaſure
    -0.86
     purpoſe
    -0.86
     fubject
    -0.86
     Monfieur
    -0.85
     Reſ
    -0.84
     ſub
    -0.84
    POSITIVE LOGITS
    BeforeMethod
    0.63
    ,
    0.61
     lenker
    0.60
     peran
    0.58
     particuli
    0.58
    日閲覧
    0.58
     eben
    0.57
    Controllo
    0.57
    pecific
    0.53
    WEBPACK
    0.52
    Activations Density 0.822%

    No Known Activations