© 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. 9084
    Prev
    Next
    INDEX
    Explanations

    text with hyphenated words, often names, especially those of Arabic origin

    oai_token-act-pair · gemini-2.0-flash

    Location categories

    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
     raiſ
    -1.04
     myſelf
    -1.02
     Efq
    -1.01
     uſed
    -0.99
     whoſe
    -0.92
     Jefus
    -0.92
     Majefty
    -0.91
     ſhe
    -0.90
     himſelf
    -0.89
     itſelf
    -0.89
    POSITIVE LOGITS
     nakalista
    0.56
    Orléans
    0.50
     Circuits
    0.47
    León
    0.47
     piaci
    0.45
     vien
    0.44
     TestBed
    0.44
     EdgeInsets
    0.44
     Modulation
    0.44
    Lö
    0.43
    Activations Density 5.287%

    No Known Activations