© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    a few specific proper nouns, potentially related to a specific company or organization

    oai_token-act-pair · gemini-2.0-flash

    Mixed languages/code

    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
     myſelf
    -1.30
     Efq
    -1.28
     Anſ
    -1.27
     Houſe
    -1.24
     Theſe
    -1.21
     Reſ
    -1.21
     Monfieur
    -1.21
     Diſ
    -1.20
     itſelf
    -1.20
     Majefty
    -1.18
    POSITIVE LOGITS
     als
    0.48
     last
    0.46
     om
    0.44
     die
    0.43
    last
    0.42
     ra
    0.40
     ge
    0.40
     w
    0.39
     van
    0.39
    he
    0.38
    Activations Density 0.079%

    No Known Activations