© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 12795
    Prev
    Next
    INDEX
    Explanations

    references like [@R12345]

    oai_token-act-pair · gemini-2.0-flash

    scientific references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     greateſt
    -0.71
     purpoſe
    -0.70
    EndInit
    -0.70
     Majefty
    -0.69
     $_"
    -0.69
     pleaſure
    -0.67
     ſtand
    -0.67
     ſever
    -0.67
     ſeveral
    -0.66
     auffi
    -0.66
    POSITIVE LOGITS
     po
    0.57
    BeginContext
    0.53
     w
    0.49
    <bos>
    0.49
    Tikang
    0.48
     E
    0.47
     W
    0.45
    EndProject
    0.45
     Po
    0.43
     по
    0.43
    Activations Density 1.485%

    No Known Activations