© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    legal citations and context

    oai_token-act-pair · gemini-2.0-flash

    Period

    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
     useContext
    -0.57
    MessageTagHelper
    -0.56
    oa̍t
    -0.56
     ninth
    -0.50
     simplifié
    -0.47
    olastic
    -0.47
    indale
    -0.47
    róleo
    -0.45
    Viitteet
    -0.44
     opérateur
    -0.44
    POSITIVE LOGITS
    6
    0.90
    5
    0.81
     six
    0.80
    ６
    0.75
    ５
    0.72
     Six
    0.69
     sixth
    0.69
     five
    0.66
     sixty
    0.66
     Sixth
    0.65
    Activations Density 9.610%

    No Known Activations