© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12173
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or presence of something with location or direction.

    oai_token-act-pair · gemini-2.0-flash

    out

    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
     للمعارف
    -0.66
    rungsseite
    -0.59
    RectangleBorder
    -0.55
    eer
    -0.54
    ette
    -0.52
    ek
    -0.49
     متعلقه
    -0.49
    ed
    -0.49
    ey
    -0.48
    ely
    -0.48
    POSITIVE LOGITS
     out
    1.01
    out
    0.84
    Out
    0.82
     OUT
    0.80
     of
    0.78
    OUT
    0.77
     Out
    0.76
    outs
    0.62
    said
    0.57
    voted
    0.56
    Activations Density 21.187%

    No Known Activations