© 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. 13987
    Prev
    Next
    INDEX
    Explanations

    words related to software licensing, distribution, and copyright

    oai_token-act-pair · gemini-2.0-flash

    Code and configuration files

    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
    ratulations
    -1.34
    polation
    -1.19
    encils
    -1.18
    hematical
    -1.18
    amemnon
    -1.09
    othesis
    -1.09
    gnition
    -1.08
    nicity
    -1.06
    AddTagHelper
    -1.05
    acherous
    -1.03
    POSITIVE LOGITS
    ou
    0.84
    um
    0.82
    us
    0.82
    ys
    0.79
    ti
    0.78
    ut
    0.77
    ma
    0.76
    me
    0.76
    pe
    0.76
    ik
    0.76
    Activations Density 21.236%

    No Known Activations