© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7223
    Prev
    Next
    INDEX
    Explanations

    names of people (with some false positives due to hyphenated words)

    oai_token-act-pair · gemini-2.0-flash

    Spanish last names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    AndroidJUnit
    -0.66
     snippetHide
    -0.61
    !")
    -0.60
    LookAnd
    -0.59
    ніципалі
    -0.59
    rungsseite
    -0.58
    ImageContext
    -0.57
    })`
    -0.57
    ')")
    -0.57
     useAuth
    -0.56
    POSITIVE LOGITS
    Дереккөздер
    0.50
    apsed
    0.43
    brokes
    0.43
     propOrder
    0.42
    exemplar
    0.42
    Reprints
    0.42
    optarg
    0.41
    dominal
    0.41
    pleft
    0.41
     sàng
    0.41
    Activations Density 0.742%

    No Known Activations