© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14603
    Prev
    Next
    INDEX
    Explanations

    language relating to charitable giving or non-profit status

    oai_token-act-pair · gemini-2.0-flash

    charities and donations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     donate
    -2.56
     donated
    -2.36
     donor
    -2.34
     donating
    -2.34
     donation
    -2.33
     donors
    -2.30
     donations
    -2.23
     Donors
    -2.19
     charity
    -2.19
     Donation
    -2.16
    POSITIVE LOGITS
    ch
    0.44
     consultato
    0.40
    PreferredItem
    0.40
    чном
    0.40
    ses
    0.39
    ческое
    0.37
     ve
    0.36
    is
    0.35
    execSQL
    0.35
    ipedi
    0.35
    Activations Density 1.314%

    No Known Activations