© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11038
    Prev
    Next
    INDEX
    Explanations

    words or short phrases that have no clear relationship to each other

    oai_token-act-pair · gemini-2.0-flash

    technical, scientific texts

    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
    SourceChecksum
    -0.90
    rungsseite
    -0.76
    MigrationBuilder
    -0.73
    tagHelperRunner
    -0.63
    Gambas
    -0.62
     ouvriers
    -0.60
     AssemblyCulture
    -0.60
     jouets
    -0.59
     quelcon
    -0.59
    mybatisplus
    -0.58
    POSITIVE LOGITS
     TIC
    0.53
     CE
    0.53
    NG
    0.53
     subdivisions
    0.53
     Gele
    0.52
     reac
    0.52
     CAS
    0.52
     cier
    0.51
     ES
    0.51
    AE
    0.51
    Activations Density 13.202%

    No Known Activations