© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9796
    Prev
    Next
    INDEX
    Explanations

    instances of the word "allow" and other words with similar meanings, like "enable", where something becomes permissible or feasible.

    oai_token-act-pair · gemini-2.0-flash

    allow

    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
     meu
    -0.47
    Why
    -0.43
    How
    -0.41
    my
    -0.40
    There
    -0.39
     meiner
    -0.39
     cordes
    -0.38
     mein
    -0.37
     meus
    -0.37
     minha
    -0.37
    POSITIVE LOGITS
    LookAnd
    1.18
     unknownFields
    1.09
    IsMutable
    0.96
    GEBURTSDATUM
    0.93
    Personensuche
    0.92
     AttributeSet
    0.91
    OrBuilder
    0.91
    fjspx
    0.91
    ReusableCell
    0.91
    AccessorTable
    0.89
    Activations Density 9.184%

    No Known Activations