© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4055
    Prev
    Next
    INDEX
    Explanations

    uncommon words and possible misspellings as well as names including compound names

    oai_token-act-pair · gemini-2.0-flash

    Har

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Har
    -1.34
    Har
    -1.27
     HAR
    -1.08
     har
    -1.06
    har
    -1.03
    HAR
    -0.92
     purpoſe
    -0.78
     Harp
    -0.74
     Audiodateien
    -0.73
     HARR
    -0.71
    POSITIVE LOGITS
     floor
    0.57
     Floor
    0.44
     off
    0.43
     forum
    0.43
    floor
    0.42
     palm
    0.42
    Floor
    0.42
    Off
    0.42
     Off
    0.41
     stik
    0.41
    Activations Density 10.493%

    No Known Activations