© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9957
    Prev
    Next
    INDEX
    Explanations

    sentences, or parts of sentences, that express argumentitive points or opinions on a topic, or it finds lists of items on a list

    oai_token-act-pair · gemini-2.0-flash

    news articles

    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
    ftagPool
    -0.67
    PerformLayout
    -0.66
    bootstrapcdn
    -0.64
    +#+#
    -0.63
    QMetaType
    -0.63
     otomatig
    -0.60
    __*/
    -0.56
    windowFixed
    -0.56
    УДК
    -0.55
     utafitiHapana
    -0.55
    POSITIVE LOGITS
     kysy
    0.52
     noDo
    0.51
     useNavigate
    0.45
    Infer
    0.44
    criminate
    0.43
     mukana
    0.43
     dAtA
    0.42
    ējās
    0.42
     näky
    0.42
     faces
    0.41
    Activations Density 12.604%

    No Known Activations