© 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. 7136
    Prev
    Next
    INDEX
    Explanations

    text relating to payments and funding

    oai_token-act-pair · gemini-2.0-flash

    finance, money, payments

    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
     Meksiku
    -0.75
    adaptiveStyles
    -0.75
    abetes
    -0.71
     يتيمه
    -0.70
    StoryboardSegue
    -0.67
     виправивши
    -0.65
     check
    -0.65
     checking
    -0.64
     Checking
    -0.64
     checks
    -0.63
    POSITIVE LOGITS
    DockStyle
    0.47
     dos
    0.43
     œuvres
    0.42
     AttributeSet
    0.41
     telur
    0.41
     النف
    0.41
    indd
    0.41
    AxisAlignment
    0.40
    addPreferredGap
    0.39
     skr
    0.39
    Activations Density 2.198%

    No Known Activations