© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4904
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to heating/heat and proportions

    oai_token-act-pair · gemini-2.0-flash

    heating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     pleaſure
    -1.09
     Cæsar
    -0.92
     deſt
    -0.88
     reaſon
    -0.86
     ſche
    -0.85
     juſ
    -0.84
     purpoſe
    -0.83
     Republics
    -0.83
     diſt
    -0.82
     Monfieur
    -0.82
    POSITIVE LOGITS
    :✨
    0.73
    enterOuterAlt
    0.64
    EndInit
    0.63
    LabelTagHelper
    0.63
     him
    0.63
     x
    0.62
     her
    0.62
     dan
    0.61
     he
    0.61
     z
    0.60
    Activations Density 1.705%

    No Known Activations