© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8534
    Prev
    Next
    INDEX
    Explanations

    the word "gain" or "gaining"

    oai_token-act-pair · gemini-2.0-flash

    terms related to gaining or increase

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

    gain

    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
    upy
    -0.44
    istics
    -0.44
     gain
    -0.44
    wachen
    -0.42
    pulsar
    -0.42
     contemplate
    -0.42
    Period
    -0.41
     period
    -0.41
    removeChild
    -0.40
    Diary
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.86
     favour
    0.80
    tvguidetime
    0.76
    IsContent
    0.76
    ⓧ
    0.74
     favor
    0.73
     виправивши
    0.68
     ujednoznacz
    0.68
    InjectAttribute
    0.67
    :+:
    0.66
    Activations Density 1.368%

    No Known Activations