© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2553
    Prev
    Next
    INDEX
    Explanations

    single digits and mentions of dates

    oai_token-act-pair · gemini-2.0-flash

    Dates and times

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     jScrollPane
    -0.57
    RUnlock
    -0.50
    ']));
    -0.46
     Comissão
    -0.45
    #+#
    -0.43
     sti
    -0.42
     povezave
    -0.42
     esternos
    -0.42
     pap
    -0.42
    ])){
    -0.42
    POSITIVE LOGITS
    ArgsConstructor
    0.73
     Starring
    0.56
     unsalted
    0.55
     Superhosts
    0.55
    uggles
    0.53
     jadx
    0.52
    StoryboardSegue
    0.52
    ضايا
    0.52
    UnknownFieldSet
    0.52
     intervening
    0.51
    Activations Density 5.283%

    No Known Activations