© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15515
    Prev
    Next
    INDEX
    Explanations

    gibberish alphanumeric strings

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    FormState
    -0.48
    illerato
    -0.46
    書館
    -0.45
    юрпри
    -0.45
     tournée
    -0.44
    ombies
    -0.42
     województ
    -0.41
    Hochspringen
    -0.41
    SharedCtor
    -0.41
    tômes
    -0.41
    POSITIVE LOGITS
    contentLoaded
    0.99
     Италијани
    0.65
    extAlignment
    0.64
     protoimpl
    0.60
    XmlAccessorType
    0.56
    MigrationBuilder
    0.55
    #+#
    0.54
    UnusedPrivate
    0.53
     Arquivado
    0.53
    SMTP
    0.52
    Activations Density 7.810%

    No Known Activations