© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 10832
    Prev
    Next
    INDEX
    Explanations

    words related to mental health and substance use

    oai_token-act-pair · gemini-2.0-flash

    emotion/mood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    utilisons
    -0.46
    Bukan
    -0.44
    lographic
    -0.43
    blätter
    -0.43
    ösung
    -0.43
    RTLI
    -0.42
    anshi
    -0.42
    lography
    -0.42
    Penjelasan
    -0.41
     Bukan
    -0.41
    POSITIVE LOGITS
     sadness
    1.24
     sad
    1.20
     happy
    1.17
     unhappiness
    1.15
     happiness
    1.13
     unhappy
    1.13
    happy
    1.05
     joy
    1.00
    contentLoaded
    1.00
    sad
    0.98
    Activations Density 2.859%

    No Known Activations