© 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. 14282
    Prev
    Next
    INDEX
    Explanations

    instances of someone addressing or referring to writing/poems

    oai_token-act-pair · gemini-2.0-flash

    Poetry

    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
     poetry
    -1.84
     poet
    -1.76
     poetic
    -1.68
     poem
    -1.68
     Poetry
    -1.67
     poets
    -1.59
     poems
    -1.59
     Poet
    -1.56
    poetry
    -1.55
    Poetry
    -1.52
    POSITIVE LOGITS
    SourceChecksum
    0.61
     Clearwater
    0.58
    enschappelijke
    0.50
    tahui
    0.49
     Schilling
    0.49
     Constantine
    0.49
    Datuak
    0.47
     Sandi
    0.46
    mögens
    0.44
    RenderAtEndOf
    0.44
    Activations Density 0.721%

    No Known Activations