© 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. 13908
    Prev
    Next
    INDEX
    Explanations

    months and dates

    oai_token-act-pair · gemini-2.0-flash

    dates and months

    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
     chi̍t
    -0.51
    PutMapping
    -0.51
    bellar
    -0.48
     Wikimedijinoj
    -0.47
    礁
    -0.45
    Filmographie
    -0.45
    rawDesc
    -0.44
     TestBed
    -0.44
    DidLoad
    -0.44
     mapStateToProps
    -0.43
    POSITIVE LOGITS
    sproz
    0.52
    ýš
    0.51
    uberge
    0.49
    pannt
    0.48
    matchCondition
    0.48
     שוליים
    0.47
    adze
    0.47
    wußt
    0.47
    명
    0.47
     entendu
    0.46
    Activations Density 0.548%

    No Known Activations