© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8891
    Prev
    Next
    INDEX
    Explanations

    a variety of terms relating to mental and emotional states, good and bad, particularly in relation to existential questions and poetry.

    oai_token-act-pair · gemini-2.0-flash

    lyrics/poetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     kasarigan
    -0.70
    parsedMessage
    -0.46
    NewRow
    -0.43
    Derbyniad
    -0.41
    messageInfo
    -0.38
    yyah
    -0.38
    szönöm
    -0.37
     aquele
    -0.37
    Erreferentziak
    -0.36
     propof
    -0.36
    POSITIVE LOGITS
    InputBorder
    0.74
     تضيفلها
    0.73
     الحره
    0.71
     '\\;'
    0.62
    MLLoader
    0.61
    DockStyle
    0.59
    TintMode
    0.59
    GenerationType
    0.57
    #+#
    0.57
    <()>
    0.57
    Activations Density 3.935%

    No Known Activations