© 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. 8104
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    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
    scribers
    -0.67
    photographe
    -0.67
    mereka
    -0.63
    nourriture
    -0.61
     purpoſe
    -0.61
    mieszkanie
    -0.60
    astéroïdes
    -0.60
    couverture
    -0.60
    tersebut
    -0.60
    ximately
    -0.59
    POSITIVE LOGITS
    sen
    0.66
    ::__
    0.62
    u
    0.59
    GFP
    0.58
    }}_{
    0.57
    }}^{
    0.57
    z
    0.56
    ru
    0.55
    tg
    0.54
    }}_{\
    0.54
    Activations Density 11.814%

    No Known Activations