© 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. 6692
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and descriptive phrases expressing approval, quality, or value.

    oai_token-act-pair · gemini-2.0-flash

    Various topics

    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
    enumi
    -0.65
    ifflin
    -0.48
     referenties
    -0.48
     ótimo
    -0.47
    Hochspringen
    -0.47
     pinulongan
    -0.44
    IBarButtonItem
    -0.44
     ótima
    -0.44
     ottimo
    -0.43
     Référence
    -0.42
    POSITIVE LOGITS
     fubject
    0.71
     houſe
    0.71
     itſelf
    0.70
     ſtate
    0.68
    StoreMessageInfo
    0.68
     ftate
    0.66
     Houſe
    0.66
     diſt
    0.65
     Efq
    0.65
     tranſ
    0.64
    Activations Density 6.595%

    No Known Activations