© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7478
    Prev
    Next
    INDEX
    Explanations

    a mix of common grammatical words (pronouns, prepositions, conjunctions) and verbs.

    oai_token-act-pair · gemini-2.0-flash

    cleaning actions

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

    Cleaning

    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
     alleg
    -0.47
    TintMode
    -0.47
    Aur
    -0.45
    AutoScaleMode
    -0.44
     tolerant
    -0.44
    stad
    -0.44
    "><?=
    -0.43
    Kota
    -0.43
    alore
    -0.43
     Toler
    -0.42
    POSITIVE LOGITS
     washing
    0.99
     scrubbing
    0.87
     washed
    0.84
    Washing
    0.83
     vacuum
    0.82
     Washing
    0.82
    washing
    0.82
     wiping
    0.80
     wash
    0.80
     cleaned
    0.78
    Activations Density 2.761%

    No Known Activations