© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11059
    Prev
    Next
    INDEX
    Explanations

    positive sentiment about ease and simplicity

    oai_token-act-pair · gemini-2.0-flash

    something is easy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     easy
    -1.30
    easy
    -1.27
     Easy
    -1.27
    Easy
    -1.25
     easier
    -1.16
     faciles
    -1.13
     fáciles
    -1.11
    Easier
    -1.07
     easily
    -1.07
     easiest
    -1.06
    POSITIVE LOGITS
     ujednoznacz
    0.46
     estimés
    0.44
    bronn
    0.41
    :].
    0.41
    begingroup
    0.39
    Fir
    0.38
    OGND
    0.38
     celib
    0.38
    ฝ
    0.38
    hamcrest
    0.38
    Activations Density 1.483%

    No Known Activations