© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12660
    Prev
    Next
    INDEX
    Explanations

    the letter "i" in code snippets

    oai_token-act-pair · gemini-2.0-flash

    variable names or identifiers in code

    np_token-act-pair-logits · gpt-4o-mini

    i

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AutoScaleMode
    -0.74
     beginnetje
    -0.67
     ✭✭
    -0.66
    الحياه
    -0.64
    @[+][
    -0.64
    wpi
    -0.63
    CloseOperation
    -0.62
     مرئيه
    -0.60
    zzleHttp
    -0.59
    inkel
    -0.59
    POSITIVE LOGITS
     województwie
    0.54
     ramai
    0.50
     ejus
    0.46
     trovar
    0.43
    usermodel
    0.40
    Jürgen
    0.38
    ότη
    0.38
    뀐
    0.37
     للمعارف
    0.37
    and
    0.36
    Activations Density 1.336%

    No Known Activations