© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5889
    Prev
    Next
    INDEX
    Explanations

    sentences about the costs of courses and student financial aid or about setting up a meeting with an advisor

    oai_token-act-pair · gemini-2.0-flash

    school financial assistance

    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
     estekak
    -0.80
     виправивши
    -0.71
     cherchés
    -0.68
     مرئيه
    -0.67
     ivelany
    -0.66
    قایناق‌لار
    -0.65
    matchCondition
    -0.65
    StoryboardSegue
    -0.64
     CGPoint
    -0.60
    DockStyle
    -0.59
    POSITIVE LOGITS
     FetchType
    0.52
    aira
    0.50
    cuál
    0.45
    RenderAtEndOf
    0.41
    ductory
    0.41
    ๊ก
    0.41
     Stack
    0.41
     brauchen
    0.41
    Stack
    0.40
    etak
    0.40
    Activations Density 0.607%

    No Known Activations