© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16190
    Prev
    Next
    INDEX
    Explanations

    code snippets and associated text with date/time formatting and also captures elements of conversation

    oai_token-act-pair · gemini-2.0-flash

    Code and data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     u
    -1.32
     d
    -1.31
     r
    -1.27
     b
    -1.26
     h
    -1.25
     p
    -1.17
     m
    -1.17
     y
    -1.13
     s
    -1.13
     c
    -1.13
    POSITIVE LOGITS
     ſever
    0.77
     quæ
    0.74
     purpoſe
    0.71
    Tikang
    0.71
     ſta
    0.70
     ſche
    0.69
     houſe
    0.69
     raiſ
    0.68
     ſtre
    0.67
     habet
    0.66
    Activations Density 5.227%

    No Known Activations