© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12325
    Prev
    Next
    INDEX
    Explanations

    words and phrases that might appear in fantasy or travel writing

    oai_token-act-pair · gemini-2.0-flash

    or, to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ^(@)
    -0.73
     Theſe
    -0.72
     Jefus
    -0.70
    WriteBarrier
    -0.70
     himſelf
    -0.69
     themſelves
    -0.69
     itſelf
    -0.66
     iſt
    -0.66
    ſelf
    -0.65
     Efq
    -0.65
    POSITIVE LOGITS
     initComponents
    0.57
     متعلقه
    0.54
     GenerationType
    0.49
     go
    0.44
    addPreferredGap
    0.43
    pg
    0.40
    nert
    0.39
    vocato
    0.39
    pota
    0.38
    zadas
    0.38
    Activations Density 0.436%

    No Known Activations