© 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. 15658
    Prev
    Next
    INDEX
    Explanations

    text related to charitable giving campaigns

    oai_token-act-pair · gemini-2.0-flash

    fundraising and business

    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
    ίδι
    -0.48
     [*]
    -0.48
     cân
    -0.45
    вара
    -0.45
     noqa
    -0.45
     Bank
    -0.44
     ingles
    -0.43
     ancestors
    -0.43
    ारा
    -0.42
     narrator
    -0.41
    POSITIVE LOGITS
    ISupport
    0.65
    DockStyle
    0.64
     calendriers
    0.63
     ContentValues
    0.61
    AutoScaleMode
    0.60
     advancement
    0.59
    Development
    0.57
    specialchars
    0.57
     Development
    0.56
     Италијани
    0.56
    Activations Density 1.096%

    No Known Activations