© 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. 6303
    Prev
    Next
    INDEX
    Explanations

    first-person language used when speaking about death

    oai_token-act-pair · gemini-2.0-flash

    Sad and reflective texts

    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
     fire
    -0.51
    лимпи
    -0.49
    gemeester
    -0.48
    ниципа
    -0.48
    rinfo
    -0.47
    rental
    -0.47
     rental
    -0.47
    !*\
    -0.46
    Uninitialized
    -0.45
     cycl
    -0.45
    POSITIVE LOGITS
     relâche
    0.58
    Geplaatst
    0.57
    windowFixed
    0.55
     للاسماء
    0.54
    ArrowToggle
    0.54
    AndEndTag
    0.54
    ագրություններ
    0.53
     AppCompatTheme
    0.53
    })^
    0.50
     die
    0.50
    Activations Density 13.238%

    No Known Activations