© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15286
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "need to be"

    oai_token-act-pair · gemini-2.0-flash

    words indicating necessity or requirement

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

    need

    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
    被
    -1.02
     được
    -0.99
     worden
    -0.95
     被
    -0.91
     being
    -0.90
    ถูก
    -0.88
     wordt
    -0.85
    being
    -0.83
    都被
    -0.81
    被他
    -0.78
    POSITIVE LOGITS
    tvguidetime
    0.64
     treating
    0.59
    TemporalType
    0.55
    +#+
    0.54
     doing
    0.54
     adopting
    0.53
    rimid
    0.53
    WebControls
    0.53
     redraw
    0.51
    heiro
    0.50
    Activations Density 2.351%

    No Known Activations