© 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. 15452
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "hard to"

    oai_token-act-pair · gemini-2.0-flash

    phrases or patterns indicating difficulty or disbelief

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

    to

    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
    Negative Logits
     ModelExpression
    -0.76
     AssemblyVersion
    -0.73
    Datuak
    -0.72
    +#+#
    -0.68
     versuchen
    -0.64
    weetened
    -0.63
     attemp
    -0.61
     Monfieur
    -0.60
     africains
    -0.60
     Attempt
    -0.60
    POSITIVE LOGITS
     fully
    0.48
     F
    0.45
     sum
    0.44
     Er
    0.44
     שוליים
    0.41
     combineReducers
    0.40
     Gra
    0.40
    iste
    0.40
     mô
    0.40
    enumi
    0.40
    Activations Density 1.184%

    No Known Activations