© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3225
    Prev
    Next
    INDEX
    Explanations

    numbers and the characters immediately surrounding them

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    nd
    -1.70
    ND
    -1.33
     nd
    -1.23
    nds
    -1.09
    ndl
    -1.08
    ndi
    -1.01
    ndy
    -0.98
     ND
    -0.96
    ndal
    -0.87
    Nd
    -0.84
    POSITIVE LOGITS
    st
    0.93
     st
    0.62
    ST
    0.62
    sts
    0.60
    stu
    0.54
    St
    0.53
    ste
    0.52
    stan
    0.50
    sta
    0.49
    スト
    0.49
    Activations Density 1.192%

    No Known Activations