© 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. 5916
    Prev
    Next
    INDEX
    Explanations

    descriptions with comparative observations

    oai_token-act-pair · gemini-2.0-flash

    holiday

    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
    etus
    -0.59
    cshtml
    -0.57
    MessageOf
    -0.52
    AfterViewInit
    -0.51
    archiviato
    -0.51
    +#+#
    -0.51
    ftagPool
    -0.50
    tonode
    -0.49
    AppCompat
    -0.49
     ProtoMessage
    -0.47
    POSITIVE LOGITS
     holiday
    1.75
    holiday
    1.55
    Holiday
    1.41
     HOLIDAY
    1.37
     Holiday
    1.33
     holidays
    1.16
    Holidays
    1.13
    holidays
    1.09
     Holidays
    1.08
     vacances
    0.71
    Activations Density 4.353%

    No Known Activations