© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9474
    Prev
    Next
    INDEX
    Explanations

    sentences with lots of pronouns ("he", "she", "they") and forms of the verb "to be".

    oai_token-act-pair · gemini-2.0-flash

    was were while

    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
    SourceChecksum
    -0.65
     ExecuteAsync
    -0.65
     سما
    -0.62
     nahilalakip
    -0.61
     дописавши
    -0.60
    Palmarès
    -0.60
     autorytatywna
    -0.59
    parsedMessage
    -0.59
    }">
    -0.57
    uxxxx
    -0.57
    POSITIVE LOGITS
    nsf
    0.48
    Alike
    0.47
     inv
    0.45
     BorderRadius
    0.45
    ValueGenerated
    0.45
     EconPapers
    0.44
    참고
    0.42
    preventDefault
    0.40
    sphase
    0.40
    enterOuterAlt
    0.40
    Activations Density 5.696%

    No Known Activations