© 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. 11641
    Prev
    Next
    INDEX
    Explanations

    mentions of political and legal options

    oai_token-act-pair · gemini-2.0-flash

    say "or" words

    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
    ibatis
    -0.46
     romero
    -0.41
    LikeLike
    -0.41
     seguida
    -0.41
    ày
    -0.40
    läs
    -0.40
    itattu
    -0.40
     bambú
    -0.40
     neceff
    -0.40
     noDo
    -0.40
    POSITIVE LOGITS
    or
    2.39
    OR
    1.80
    ors
    1.42
    orul
    1.38
    orite
    1.33
    orin
    1.26
    orii
    1.26
    orist
    1.24
    orar
    1.23
    orate
    1.21
    Activations Density 7.254%

    No Known Activations