© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5648
    Prev
    Next
    INDEX
    Explanations

    when something comes to an end.

    oai_token-act-pair · gemini-2.0-flash

    actions or processes related to completion or improvement

    np_token-act-pair-logits · gpt-4o-mini

    down

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     them
    -0.97
     it
    -0.73
    them
    -0.66
     things
    -0.62
     इसे
    -0.54
    ها
    -0.54
     him
    -0.53
    ∬
    -0.53
     saker
    -0.52
     eux
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.92
     down
    0.75
     up
    0.75
     out
    0.74
     ब्रेकडाउन
    0.71
    raught
    0.70
    StoryboardSegue
    0.69
     utafitiHapana
    0.69
    #+#
    0.68
     forth
    0.65
    Activations Density 1.945%

    No Known Activations