© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15399
    Prev
    Next
    INDEX
    Explanations

    occurrences of prepositions or words collocating with prepositions in a somewhat incoherent way with little semantic relationship between the activated words.

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    Many
    -0.83
     Many
    -0.73
    many
    -0.70
    Most
    -0.69
    ,
    -0.66
    most
    -0.65
     nombreuses
    -0.64
     nombreux
    -0.59
    .
    -0.57
     centaines
    -0.56
    POSITIVE LOGITS
    StoryboardSegue
    0.88
    ientôt
    0.88
     Efq
    0.86
     betweenstory
    0.85
     myſelf
    0.82
    ^(@)
    0.81
    ſelves
    0.80
    LookAnd
    0.80
    posedge
    0.79
     Walkover
    0.79
    Activations Density 7.111%

    No Known Activations