© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9334
    Prev
    Next
    INDEX
    Explanations

    words or parts of words that include "ps", "or", or "ess"

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Rüyada
    -0.62
    Rè
    -0.51
    randrange
    -0.50
    protoimpl
    -0.48
     numerus
    -0.48
    ]`
    -0.48
    momix
    -0.46
    kebox
    -0.46
    Derbyniad
    -0.45
    posables
    -0.45
    POSITIVE LOGITS
    Composable
    0.81
     Roskov
    0.66
    êmio
    0.65
    AccessorTable
    0.64
    mybatisplus
    0.64
     SPIE
    0.60
     gehe
    0.59
     guère
    0.59
     faſt
    0.57
     setType
    0.56
    Activations Density 0.673%

    No Known Activations