© 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. 833
    Prev
    Next
    INDEX
    Explanations

    code-like syntax including strings enclosed by quotes, lists in angle brackets, and function calls

    oai_token-act-pair · gemini-2.0-flash

    say "id"

    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
     ID
    -1.88
     id
    -1.70
     Id
    -1.66
    ID
    -1.55
     IDs
    -1.53
     ids
    -1.41
    IDs
    -1.37
     setId
    -1.37
    Id
    -1.35
    id
    -1.26
    POSITIVE LOGITS
     समीक्षक
    0.60
     otomatig
    0.51
    httphttps
    0.49
    றை
    0.47
    TestingModule
    0.47
     esternos
    0.47
     հղումներ
    0.46
    ########.
    0.46
    öner
    0.43
     terrain
    0.43
    Activations Density 1.016%

    No Known Activations