© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10386
    Prev
    Next
    INDEX
    Explanations

    the words "hard", "worked", and "try" and variations of them.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "hard"

    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
     BoxFit
    -0.75
     validamos
    -0.54
    InputBorder
    -0.54
     هيا
    -0.52
     Offisielt
    -0.50
     Latent
    -0.50
     Rptr
    -0.49
    StatusOK
    -0.48
    ChildScrollView
    -0.48
    Rptr
    -0.47
    POSITIVE LOGITS
     hard
    3.09
    hard
    2.63
    Hard
    2.58
     Hard
    2.53
     harder
    2.50
     HARD
    2.42
    HARD
    2.30
     hardest
    2.23
     Harder
    1.88
     harde
    1.76
    Activations Density 1.220%

    No Known Activations