© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2066
    Prev
    Next
    INDEX
    Explanations

    mentions of governing and legal concepts

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     المعيارى
    -0.78
     متعلقه
    -0.66
    Abitanti
    -0.65
     विश्वसनीयता
    -0.61
     pinulongan
    -0.58
     Autorizaciones
    -0.57
    μβρίου
    -0.57
    MigrationBuilder
    -0.57
    endphp
    -0.56
     Lightboxes
    -0.55
    POSITIVE LOGITS
     no
    3.42
    no
    2.89
     NO
    2.34
    No
    2.33
    NO
    2.25
     No
    2.16
     нет
    1.43
     kein
    1.43
     keine
    1.38
     nobody
    1.35
    Activations Density 12.566%

    No Known Activations