© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9899
    Prev
    Next
    INDEX
    Explanations

    the string "min" and common words around it like red, first, max width

    oai_token-act-pair · gemini-2.0-flash

    min

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Datuak
    -0.60
     doInBackground
    -0.58
    WaitGroup
    -0.52
    RenderAtEndOf
    -0.51
    wargs
    -0.49
    tiendo
    -0.47
     surla
    -0.45
    landes
    -0.45
    UnsafeEnabled
    -0.44
    mybatisplus
    -0.44
    POSITIVE LOGITS
    sat
    0.57
    sen
    0.56
    stick
    0.55
    SceneManagement
    0.54
    imax
    0.52
    umab
    0.51
    entine
    0.50
    جوايز
    0.49
    ska
    0.49
    });*/
    0.49
    Activations Density 8.358%

    No Known Activations