© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12629
    Prev
    Next
    INDEX
    Explanations

    words associated with goals, accomplishments, and support

    oai_token-act-pair · gemini-2.0-flash

    dream

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     dream
    -1.16
     dreams
    -1.14
    dreams
    -1.06
    dream
    -1.03
     dreamed
    -0.99
     DREAM
    -0.98
     dreamt
    -0.96
    Rüyada
    -0.92
     dreaming
    -0.92
     visions
    -0.91
    POSITIVE LOGITS
    CSharp
    0.42
    BUFFER
    0.41
     and
    0.40
    간
    0.38
    ñora
    0.37
    Zeneca
    0.37
    hit
    0.36
     écrans
    0.36
     we
    0.36
    bootstrapcdn
    0.35
    Activations Density 15.720%

    No Known Activations