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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10325
    Prev
    Next
    INDEX
    Explanations

    the journey of a company becoming a B-Corp

    oai_token-act-pair · gemini-2.0-flash

    quality control/inspection contexts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.63
    windowFixed
    -0.59
     estoppel
    -0.57
    itectura
    -0.57
     Biele
    -0.57
    ühlen
    -0.56
    jsxFileName
    -0.55
    versite
    -0.52
    oxone
    -0.52
     puissiez
    -0.52
    POSITIVE LOGITS
    DataURL
    0.54
    awakeFromNib
    0.52
     fir
    0.52
    intem
    0.50
     Foire
    0.47
    classmethod
    0.47
     ***!
    0.47
     inquirer
    0.46
    قایناق‌لار
    0.44
    protoc
    0.44
    Activations Density 0.769%

    No Known Activations