© 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. 9754
    Prev
    Next
    INDEX
    Explanations

    vague words and phrases used in discussions of opinions, feelings, senses, and community and also finds references to official status

    oai_token-act-pair · gemini-2.0-flash

    of

    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
     rapid
    -0.32
    IMENTS
    -0.31
     distinct
    -0.30
    Vanjske
    -0.30
     unique
    -0.29
     constant
    -0.29
     terrain
    -0.28
     extra
    -0.28
     un
    -0.28
     basic
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.73
     myſelf
    0.71
     feroit
    0.71
    IndentedString
    0.71
    ArrowToggle
    0.70
    AsUp
    0.69
    Попис
    0.69
    Be
    0.68
     étoit
    0.67
     auroit
    0.67
    Activations Density 38.748%

    No Known Activations