© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13133
    Prev
    Next
    INDEX
    Explanations

    times of day written in numbers

    oai_token-act-pair · gemini-2.0-flash

    Times and schedules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    saraba
    -0.93
     مشين
    -0.92
    AndEndTag
    -0.90
     resourceCulture
    -0.90
    SequentialGroup
    -0.85
    CodedInputStream
    -0.83
    findpost
    -0.77
     disambiguazione
    -0.76
     Efq
    -0.75
    +#+
    -0.75
    POSITIVE LOGITS
    <eos>
    0.40
    OwnProperty
    0.38
    rupal
    0.38
     
    0.38
     C
    0.37
     "+
    0.36
     paradas
    0.35
     It
    0.35
     B
    0.35
     "
    0.35
    Activations Density 0.714%

    No Known Activations