© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3277
    Prev
    Next
    INDEX
    Explanations

    mentions of "intensity"

    oai_token-act-pair · gemini-2.0-flash

    intensity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.56
     ‘
    -0.52
     or
    -0.52
    )')
    -0.49
    grade
    -0.48
     '
    -0.47
    लाइन
    -0.47
     was
    -0.45
     „
    -0.45
    catch
    -0.44
    POSITIVE LOGITS
    rungsseite
    1.21
    VersionUID
    1.09
    Tembelea
    1.01
     larmes
    0.87
    enumi
    0.87
     cytoplasm
    0.86
    ξη
    0.84
     يتيمه
    0.82
     Elis
    0.82
     breaker
    0.81
    Activations Density 1.307%

    No Known Activations