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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13340
    Prev
    Next
    INDEX
    Explanations

    question/answer pairs and code snippets in what looks like online forum posts

    oai_token-act-pair · gemini-2.0-flash

    !

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ++)
    -0.56
    Viitteet
    -0.51
    apunov
    -0.50
    Lähteet
    -0.49
     урна
    -0.47
     na
    -0.46
    стви
    -0.46
    打
    -0.46
     <=",
    -0.46
    لسل
    -0.45
    POSITIVE LOGITS
     Paglinawan
    0.56
    InitStruct
    0.52
    GeneratedMessage
    0.48
     abstinence
    0.46
     Roskov
    0.45
     Merry
    0.45
    nsic
    0.45
    سمبر
    0.44
    NetworkInfo
    0.44
     extradition
    0.44
    Activations Density 0.905%

    No Known Activations