© 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. 5541
    Prev
    Next
    INDEX
    Explanations

    the word "char" with various capitalizations and surrounding context

    oai_token-act-pair · gemini-2.0-flash

    char

    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
     RIDGE
    -0.51
    useState
    -0.50
    igans
    -0.50
    vierno
    -0.48
    κι
    -0.48
    Credit
    -0.47
     Kredit
    -0.47
     Ridge
    -0.47
    superuser
    -0.47
     Credit
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.75
    lottes
    0.71
     Савезне
    0.67
    fromnode
    0.62
    +#+#
    0.59
    verwijspagina
    0.58
     oprot
    0.58
     Bioaccumulative
    0.58
    AddTagHelper
    0.57
    iotensin
    0.57
    Activations Density 0.459%

    No Known Activations