© 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. 858
    Prev
    Next
    INDEX
    Explanations

    time-related words, especially those indicating a specific period

    oai_token-act-pair · gemini-2.0-flash

    school year

    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
     season
    -1.75
    season
    -1.49
     SEASON
    -1.48
    Season
    -1.48
     Season
    -1.48
     seasons
    -1.25
    SEASON
    -1.24
     saison
    -1.16
     temporada
    -1.06
     saisons
    -1.04
    POSITIVE LOGITS
    Становништво
    0.59
    FailureListener
    0.46
     newData
    0.44
    SCAPE
    0.43
     drying
    0.43
    ībā
    0.42
     Шта
    0.41
    addContainerGap
    0.41
    spod
    0.40
    στι
    0.40
    Activations Density 3.049%

    No Known Activations