© 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. 5601
    Prev
    Next
    INDEX
    Explanations

    math questions asking to find the nth term of a sequence

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    LookAnd
    -1.10
    IUrlHelper
    -1.05
    featureID
    -1.01
    tagHelperRunner
    -1.00
    GEBURTSDATUM
    -0.98
     CreateTagHelper
    -0.96
     OFDb
    -0.94
    EndProject
    -0.93
     समीक्षाओं
    -0.90
    webElementXpaths
    -0.89
    POSITIVE LOGITS
     linear
    0.48
     non
    0.46
     su
    0.44
     tre
    0.44
    th
    0.43
     ca
    0.43
    pl
    0.42
     des
    0.41
     ver
    0.41
    ward
    0.41
    Activations Density 3.534%

    No Known Activations