© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12380
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical procedures and research studies involving patients

    oai_token-act-pair · gemini-2.0-flash

    experience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ﷺ
    -0.45
    Normdaten
    -0.45
    onAttach
    -0.44
    validates
    -0.43
    ที
    -0.43
    hdashline
    -0.42
     cuello
    -0.40
    وط
    -0.40
     WARRANTIES
    -0.40
     Plot
    -0.40
    POSITIVE LOGITS
     experience
    2.86
    experience
    2.55
     Experience
    2.53
    Experience
    2.45
     experiences
    2.44
     EXPERIENCE
    2.36
    experiences
    2.19
    EXPERIENCE
    2.13
     Experiences
    2.13
     expérience
    2.11
    Activations Density 2.726%

    No Known Activations