© 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. 1008
    Prev
    Next
    INDEX
    Explanations

    descriptions of signal processing and hardware systems, with a focus on filters and synchronization

    oai_token-act-pair · gemini-2.0-flash

    filtering

    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
     filter
    -2.70
     filters
    -2.66
     Filter
    -2.58
     filtering
    -2.53
     Filters
    -2.52
     filtered
    -2.44
    Filter
    -2.42
     FILTER
    -2.39
    filter
    -2.36
    FILTER
    -2.30
    POSITIVE LOGITS
     MainAxisSize
    0.62
     Roskov
    0.59
    kháu
    0.58
    SequentialGroup
    0.57
    balleur
    0.53
    Nazionale
    0.52
     recommandée
    0.52
    NameValuePair
    0.52
    Xna
    0.51
    enterOuterAlt
    0.51
    Activations Density 1.686%

    No Known Activations