© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3690
    Prev
    Next
    INDEX
    Explanations

    sentences that contain references to groups of people facing a challenge.

    oai_token-act-pair · gemini-2.0-flash

    say "-ing" 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
     a
    -0.65
    tvguidetime
    -0.57
     present
    -0.56
    by
    -0.54
    Xna
    -0.53
     MotionEvent
    -0.53
    present
    -0.52
     by
    -0.52
    Present
    -0.50
     Present
    -0.50
    POSITIVE LOGITS
     running
    0.86
     flying
    0.84
     living
    0.84
     riding
    0.80
     serving
    0.78
     operating
    0.77
     selling
    0.77
     working
    0.75
     holding
    0.75
     printing
    0.74
    Activations Density 10.881%

    No Known Activations