© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11256
    Prev
    Next
    INDEX
    Explanations

    words that suggest something is "more" or "less" compared to something else

    oai_token-act-pair · gemini-2.0-flash

    high

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     high
    -1.34
    high
    -1.20
     High
    -1.20
    High
    -1.20
     HIGH
    -0.90
    高
    -0.88
    HIGH
    -0.85
     low
    -0.82
    low
    -0.79
    <bos>
    -0.74
    POSITIVE LOGITS
     doubtnut
    1.00
     Houſe
    0.89
     للمعارف
    0.87
     Reſ
    0.85
     autorytatywna
    0.84
    IsMutable
    0.84
    MENAFN
    0.81
     Exacts
    0.81
     raiſ
    0.79
     Diſ
    0.79
    Activations Density 0.738%

    No Known Activations