© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods

    oai_token-act-pair · gemini-2.0-flash

    early or late

    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
    ########.
    -0.66
     QtCore
    -0.59
    Erreferentziak
    -0.58
    +#+#
    -0.56
    Izvori
    -0.55
    XtraBars
    -0.54
    localScale
    -0.54
    niña
    -0.53
    setViewportView
    -0.52
     Roskov
    -0.51
    POSITIVE LOGITS
    ArgsConstructor
    0.52
    going
    0.47
     pleaſure
    0.45
     goi
    0.45
     gepubliceerd
    0.45
     Eſ
    0.45
     Ede
    0.44
    -'
    0.44
     mì
    0.44
    argate
    0.43
    Activations Density 8.877%

    No Known Activations