© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11539
    Prev
    Next
    INDEX
    Explanations

    words or phrases describing results or effects

    oai_token-act-pair · gemini-2.0-flash

    consequences

    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
     photolibrary
    -1.31
     Efq
    -1.29
     Theſe
    -1.17
     Monfieur
    -1.16
     doubtnut
    -1.14
     Majefty
    -1.12
     Diſ
    -1.10
     myſelf
    -1.08
     soldati
    -1.07
     raiſ
    -1.05
    POSITIVE LOGITS
     
    0.80
    '
    0.74
    ’
    0.66
     av
    0.65
     das
    0.65
     next
    0.65
     r
    0.64
     e
    0.61
     đ
    0.60
     number
    0.60
    Activations Density 3.589%

    No Known Activations