© 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. 13862
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "is" and adverbs like "probably", "also", "really"

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    Spoljašnje
    -0.56
     utili
    -0.53
    πάρχ
    -0.50
    Predecesor
    -0.50
     Responsible
    -0.50
    inguish
    -0.49
    lops
    -0.48
    )';
    -0.48
    }',
    -0.47
    IMAS
    -0.47
    POSITIVE LOGITS
     CURIAM
    0.67
    AtIndexPath
    0.66
     fusca
    0.65
    الدراسه
    0.60
     quæ
    0.59
    dubbo
    0.58
    исленность
    0.58
     noastre
    0.57
    ContentAsync
    0.56
    writeFieldEnd
    0.56
    Activations Density 3.799%

    No Known Activations