© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10336
    Prev
    Next
    INDEX
    Explanations

    the word 'remains' and phrases indicating something yet to be done or something that persists

    oai_token-act-pair · gemini-2.0-flash

    remains

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     remain
    -1.93
     remains
    -1.87
     remaining
    -1.81
     remained
    -1.63
    remain
    -1.59
     Remaining
    -1.57
    <bos>
    -1.51
    remains
    -1.44
     Remain
    -1.42
    remaining
    -1.41
    POSITIVE LOGITS
     NSCoder
    0.83
     AppComponent
    0.64
    ContentAsync
    0.60
    antMatchers
    0.56
    PropertyChanging
    0.56
    Composable
    0.55
    tvguidetime
    0.55
    ãng
    0.54
    IsMutable
    0.54
    cshtml
    0.53
    Activations Density 3.500%

    No Known Activations