© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3556
    Prev
    Next
    INDEX
    Explanations

    HTML form-related tags and attributes

    oai_token-act-pair · gemini-2.0-flash

    say = sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     auroit
    -0.84
     avoient
    -0.84
     enfans
    -0.82
     Monfieur
    -0.81
     fédé
    -0.80
     aveug
    -0.80
     Efq
    -0.79
     étoient
    -0.79
     colorés
    -0.79
     purpoſe
    -0.77
    POSITIVE LOGITS
    ="#"><
    0.54
    ="#">
    0.49
    ="<?=
    0.46
    ForResult
    0.45
    ="#"
    0.45
     insuffisamment
    0.42
    modb
    0.41
    ="<?
    0.40
    BASEPATH
    0.40
    ="{{$
    0.39
    Activations Density 6.264%

    No Known Activations