© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10587
    Prev
    Next
    INDEX
    Explanations

    the number 1, sometimes followed by other digits

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    th
    -1.77
    TH
    -1.67
     th
    -1.44
    Th
    -1.43
     TH
    -1.33
     Th
    -1.30
    ths
    -1.24
    THS
    -1.10
    thi
    -1.07
    tho
    -1.02
    POSITIVE LOGITS
    nd
    0.85
    st
    0.84
     nd
    0.66
    rd
    0.52
    nds
    0.51
    stow
    0.51
    ND
    0.50
    قایناق‌لار
    0.49
    stin
    0.47
    sts
    0.46
    Activations Density 0.774%

    No Known Activations