© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6564
    Prev
    Next
    INDEX
    Explanations

    a mix of things which may reflect multiple functions. It finds financial terms, references to specific days, technical language related to sleep and product reviews

    oai_token-act-pair · gemini-2.0-flash

    Time and dates

    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
     last
    -3.47
     Last
    -3.25
    Last
    -3.19
    last
    -3.19
     LAST
    -2.86
    LAST
    -2.73
     dernière
    -2.28
     letzten
    -2.28
     último
    -2.25
     dernier
    -2.22
    POSITIVE LOGITS
     خارجية
    0.60
     дописавши
    0.57
    RunWith
    0.51
     useAppContext
    0.50
     onResponse
    0.50
    ValueStyle
    0.48
    tup
    0.47
     CURIAM
    0.45
     समीक्षाएं
    0.45
    mapStateToProps
    0.44
    Activations Density 4.420%

    No Known Activations