© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16109
    Prev
    Next
    INDEX
    Explanations

    the word variations of "look" or "feel", and associations with them

    oai_token-act-pair · gemini-2.0-flash

    say "like"

    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
     kinds
    -1.36
     sorts
    -1.27
     kind
    -1.26
    Kind
    -1.24
    kind
    -1.23
     Kinds
    -1.23
    kinds
    -1.20
     Kind
    -1.19
     sort
    -1.19
     types
    -1.18
    POSITIVE LOGITS
     مرئيه
    0.85
     '\\;'
    0.73
     Normdatei
    0.69
    fromnode
    0.66
     يتيمه
    0.65
     définiti
    0.64
    initis
    0.64
     doubtnut
    0.63
     Monfieur
    0.62
    aarrggbb
    0.61
    Activations Density 0.574%

    No Known Activations