© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    descriptive language, especially superlatives like "slightly" or "too" along with adjectives.

    oai_token-act-pair · gemini-2.0-flash

    Technical product descriptions

    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
    +#+#
    -0.69
     InputDecoration
    -0.61
     ProtoMessage
    -0.60
    ########.
    -0.57
    simpleType
    -0.56
    PerformLayout
    -0.55
    setVerticalGroup
    -0.55
     OMITBAD
    -0.51
    ModelBuilder
    -0.49
    FormTagHelper
    -0.48
    POSITIVE LOGITS
    twimg
    0.55
     Ordem
    0.54
     ovp
    0.51
    ContextHolder
    0.49
    Karten
    0.47
    wiec
    0.47
    Hentet
    0.47
    pement
    0.47
    valry
    0.47
     occaf
    0.47
    Activations Density 7.862%

    No Known Activations