© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6580
    Prev
    Next
    INDEX
    Explanations

    the letter 'b' and some nearby letters in seemingly random combinations, which could indicate it is identifying hexadecimal or other alphanumeric identifiers

    oai_token-act-pair · gemini-2.0-flash

    b

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    脚注の使い方
    -0.87
    BeginContext
    -0.70
    ca
    -0.60
     الحره
    -0.58
    ÇA
    -0.54
     ElevatedButton
    -0.54
     utafitiHapana
    -0.54
    KID
    -0.53
     Blackwood
    -0.53
    __);
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.61
    mybatisplus
    0.60
     >=",
    0.59
    IsMutable
    0.54
    ктей
    0.48
     appels
    0.47
    AddTagHelper
    0.46
    potranspiration
    0.46
    Біографія
    0.45
    buttonShape
    0.44
    Activations Density 2.253%

    No Known Activations