© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7759
    Prev
    Next
    INDEX
    Explanations

    the word "hard", sometimes followed by "one" or preceded by "struggle" or modified by "easy"

    oai_token-act-pair · gemini-2.0-flash

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    LookAnd
    -0.69
     Unies
    -0.62
    ไหน
    -0.59
     незавершена
    -0.59
    Tikang
    -0.56
    arraycopy
    -0.56
     تانيه
    -0.56
     FOOT
    -0.54
     <<<<<<<<<<<<<<
    -0.54
    engaruhi
    -0.53
    POSITIVE LOGITS
     difficulty
    1.30
     difficulties
    1.20
     Difficulties
    1.07
    difficulty
    1.06
     difficult
    1.01
    diffic
    0.99
     Difficult
    0.99
     Difficulty
    0.99
    difficult
    0.96
     diffic
    0.94
    Activations Density 0.109%

    No Known Activations