© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9076
    Prev
    Next
    INDEX
    Explanations

    words in a technical context, often related to procedures and results.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -0.56
    Geografie
    -0.54
    uxxxx
    -0.53
    HasColumnType
    -0.51
     Augenblick
    -0.49
    __":
    -0.48
    Sprintf
    -0.47
     للاسماء
    -0.47
    الحياه
    -0.47
    ✨:
    -0.47
    POSITIVE LOGITS
    ]<<"
    0.61
    </tfoot>
    0.59
     Viitattu
    0.54
    NewUrlParser
    0.54
    ận
    0.52
     transfieras
    0.52
    tagHelperRunner
    0.52
    unhofer
    0.52
     OnInit
    0.51
    verwijspagina
    0.50
    Activations Density 7.541%

    No Known Activations