© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8571
    Prev
    Next
    INDEX
    Explanations

    C code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash

    Portuguese

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    long-s words

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     lo
    -0.40
     na
    -0.39
     lu
    -0.36
     op
    -0.36
     le
    -0.35
     dat
    -0.35
     нас
    -0.34
     van
    -0.34
     nu
    -0.34
     sus
    -0.34
    POSITIVE LOGITS
     raiſ
    1.13
     Monfieur
    1.11
     becauſe
    1.08
     itſelf
    1.05
     Anſ
    1.04
     myſelf
    1.02
     purpoſe
    1.02
     Efq
    1.01
     uſed
    1.00
     Theſe
    1.00
    Activations Density 4.102%

    No Known Activations