© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1173
    Prev
    Next
    INDEX
    Explanations

    code and code-related terms often found in Android development snippets such as overridden functions

    oai_token-act-pair · gemini-2.0-flash

    Code related terms

    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
     myſelf
    -0.57
     poffible
    -0.54
     faſt
    -0.52
     melted
    -0.51
     himſelf
    -0.50
     themſelves
    -0.50
     Soyez
    -0.48
     Cfr
    -0.47
     unleashed
    -0.46
     deposited
    -0.46
    POSITIVE LOGITS
    gameserver
    0.83
    WebElementEntity
    0.76
     resourceCulture
    0.71
    apimachinery
    0.70
    writeFieldEnd
    0.69
    ReusableCell
    0.68
     ApiException
    0.66
    CopyWith
    0.65
    mybatisplus
    0.65
    tagHelperRunner
    0.64
    Activations Density 3.783%

    No Known Activations