© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7512
    Prev
    Next
    INDEX
    Explanations

    the number "3" as part of a date, sometimes matching words like "after" and "filed" that come before and after the date

    oai_token-act-pair · gemini-2.0-flash

    3

    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
    rungsseite
    -0.75
    ２
    -0.57
     ٢
    -0.57
     ২
    -0.55
    ３
    -0.54
    NameInMap
    -0.54
     Five
    -0.54
     twenty
    -0.53
    batore
    -0.53
    tagHelperRunner
    -0.53
    POSITIVE LOGITS
    ]='\
    0.60
    0
    0.58
     لينك
    0.51
    anskje
    0.49
    UDC
    0.46
    ]--;
    0.45
    }],
    0.43
    kapet
    0.43
    1
    0.42
    læg
    0.40
    Activations Density 5.787%

    No Known Activations