© 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. 14077
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, particularly equations with symbols like $ and fractions

    oai_token-act-pair · gemini-2.0-flash

    code and mathematics

    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
     V
    -2.09
     v
    -1.98
    V
    -1.80
    v
    -1.43
    Ｖ
    -1.36
    getV
    -1.30
    Vs
    -1.13
     VC
    -1.07
     VI
    -1.06
    VI
    -1.05
    POSITIVE LOGITS
     Efq
    0.76
     myſelf
    0.74
     سكانية
    0.71
    ")));
    0.66
     Monfieur
    0.66
    enumi
    0.66
    :]:
    0.66
     Majefty
    0.65
    eseorang
    0.65
     Theſe
    0.65
    Activations Density 1.457%

    No Known Activations