© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6513
    Prev
    Next
    INDEX
    Explanations

    positive sentiment about ease of use

    oai_token-act-pair · gemini-2.0-flash

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     myſelf
    -0.88
    ſelf
    -0.84
     itſelf
    -0.81
     iſt
    -0.81
     Efq
    -0.80
     Majefty
    -0.79
     doubtnut
    -0.78
     photolibrary
    -0.77
     fevere
    -0.75
     ſche
    -0.74
    POSITIVE LOGITS
     easy
    1.65
    easy
    1.23
     Easy
    1.23
    Easy
    1.20
     EASY
    1.17
     easily
    1.10
     easiest
    1.07
     eas
    1.05
     easier
    1.03
     leicht
    0.99
    Activations Density 1.662%

    No Known Activations