© 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. 3974
    Prev
    Next
    INDEX
    Explanations

    the word "followed" and associated words

    oai_token-act-pair · gemini-2.0-flash

    unusual formatting or special characters

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

    follow

    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
    Personendaten
    -0.70
    webElementXpaths
    -0.54
    ftagPool
    -0.52
     Follows
    -0.47
    UserScript
    -0.45
     Follow
    -0.45
    inaudible
    -0.44
     follow
    -0.44
    atigable
    -0.43
    addGap
    -0.42
    POSITIVE LOGITS
    //
    0.62
     whoſe
    0.62
    ImageContext
    0.60
     Theſe
    0.60
    PyExc
    0.60
     Monfieur
    0.60
     Aé
    0.58
    OGND
    0.56
     ſeveral
    0.56
     reaſon
    0.56
    Activations Density 9.694%

    No Known Activations