© 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. 15877
    Prev
    Next
    INDEX
    Explanations

    a handful of seemingly unrelated words, possibly indicating multiple functions or noisy data.

    oai_token-act-pair · gemini-2.0-flash

    Technical content

    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
     instance
    -0.40
    com
    -0.40
     pas
    -0.40
    í
    -0.40
    र्ड
    -0.40
     r
    -0.39
     основе
    -0.38
     Mo
    -0.38
    isu
    -0.38
    ondon
    -0.38
    POSITIVE LOGITS
     utafitiHapana
    0.81
     Савезне
    0.76
    Portale
    0.75
     MainAxisSize
    0.74
     Efq
    0.74
     विश्वसनीयता
    0.73
    moiselle
    0.73
     pinulongan
    0.71
     Reſ
    0.71
    migrationBuilder
    0.70
    Activations Density 0.243%

    No Known Activations