© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12279
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "DiCFS"

    oai_token-act-pair · gemini-2.0-flash

    Di

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     di
    -2.00
     Di
    -1.92
    Di
    -1.81
    di
    -1.53
     DI
    -1.12
    DI
    -1.03
    dip
    -1.00
     dip
    -0.99
     ди
    -0.95
    <bos>
    -0.94
    POSITIVE LOGITS
     myſelf
    0.86
     himſelf
    0.74
    expandindo
    0.73
     Efq
    0.72
     fubject
    0.71
     fevere
    0.70
    mergeFrom
    0.69
     ſtate
    0.69
     Majefty
    0.68
    ſelf
    0.68
    Activations Density 1.402%

    No Known Activations