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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11799
    Prev
    Next
    INDEX
    Explanations

    the phrase "hard to"

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating difficulty or challenge

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

    hard

    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
     ModelExpression
    -1.16
    +#+#
    -1.02
     CreateTagHelper
    -1.02
    AutoScaleMode
    -0.95
    RegressionTest
    -0.86
     surla
    -0.84
     defaultstate
    -0.79
    WebVitals
    -0.77
    AndEndTag
    -0.77
    Espèce
    -0.76
    POSITIVE LOGITS
     to
    0.83
    prest
    0.44
    iste
    0.43
     toman
    0.41
    Popis
    0.40
     for
    0.40
     when
    0.40
     Pre
    0.40
     ausz
    0.40
    break
    0.39
    Activations Density 0.754%

    No Known Activations