© 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. 2996
    Prev
    Next
    INDEX
    Explanations

    articles ("a", "the") followed by nouns or adjectives and sentence punctuation.

    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_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
     itſelf
    -1.21
     myſelf
    -1.20
     iſt
    -1.14
    ſelf
    -1.13
     pleaſure
    -1.13
     ſche
    -1.12
     ―――――
    -1.10
    ſelves
    -1.10
     purpoſe
    -1.10
     Jefus
    -1.09
    POSITIVE LOGITS
    favor
    0.39
     se
    0.38
     is
    0.36
     di
    0.35
     le
    0.35
     in
    0.35
     d
    0.34
     na
    0.34
    sold
    0.34
    terrible
    0.34
    Activations Density 11.939%

    No Known Activations