© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7346
    Prev
    Next
    INDEX
    Explanations

    code snippets, references to prior art, and the word "prior"

    oai_token-act-pair · gemini-2.0-flash

    prior

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    modelBuilder
    -0.50
    principalTable
    -0.47
     devriez
    -0.45
    GIVEREF
    -0.44
    ungguhnya
    -0.42
     mos
    -0.42
     prochains
    -0.40
    ви
    -0.40
     movimenti
    -0.40
    霄
    -0.39
    POSITIVE LOGITS
     Audiodateien
    0.68
     quid
    0.66
     $_"
    0.65
     useRouter
    0.65
    AndEndTag
    0.63
    providedIn
    0.63
     Efq
    0.63
    فایل‌لار
    0.61
     Seeder
    0.60
     BoxFit
    0.60
    Activations Density 0.963%

    No Known Activations