© 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. 4243
    Prev
    Next
    INDEX
    Explanations

    code snippets or comments, specifically in Portuguese and related to software development or scripting, possibly including mentions of visa/passport documentation

    oai_token-act-pair · 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
    DeleteBehavior
    -0.86
    ########.
    -0.64
    ConstraintMaker
    -0.63
    IBAction
    -0.62
    findpost
    -0.59
     disambiguazione
    -0.58
     JpaRepository
    -0.57
    enumii
    -0.56
    存于互联网档案馆
    -0.55
     ostavi
    -0.54
    POSITIVE LOGITS
     le
    0.52
     Le
    0.50
    järvi
    0.46
    gued
    0.46
    le
    0.45
    MessageOf
    0.45
     sel
    0.45
    computation
    0.44
    ล้ว
    0.44
    Le
    0.44
    Activations Density 0.499%

    No Known Activations