© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    code snippets, software development terminology, and philosophical comparisons

    oai_token-act-pair · gemini-2.0-flash

    similarity and comparisons

    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
     similar
    -3.22
    similar
    -3.13
     Similar
    -3.00
    Similar
    -2.98
     SIMILAR
    -2.77
     similares
    -2.39
     comparable
    -2.28
     podob
    -2.25
     similaires
    -2.22
     similaire
    -2.19
    POSITIVE LOGITS
    AsUp
    0.56
     BorderRadius
    0.52
     very
    0.50
     exact
    0.50
    meo
    0.49
    lays
    0.48
     autorité
    0.48
    uct
    0.47
    rungsseite
    0.45
    nery
    0.45
    Activations Density 8.337%

    No Known Activations