© 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. 13265
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bit" and words that add specificity or a small amount of something

    oai_token-act-pair · gemini-2.0-flash

    bit or little

    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
    rather
    -0.69
    Rather
    -0.67
    GenerationType
    -0.61
     rather
    -0.61
    TargetException
    -0.56
     Rather
    -0.54
    contentLoaded
    -0.54
    LinkId
    -0.54
     sort
    -0.52
    Sort
    -0.52
    POSITIVE LOGITS
     of
    0.63
     arşivlendi
    0.57
    Personendaten
    0.56
     Houſe
    0.56
     Majefty
    0.55
     ſeveral
    0.54
     ftate
    0.54
     myſelf
    0.54
    DockStyle
    0.54
     BoxDecoration
    0.54
    Activations Density 6.330%

    No Known Activations