© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6036
    Prev
    Next
    INDEX
    Explanations

    statistical measures of data distributions

    oai_token-act-pair · gemini-2.0-flash

    offset

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    rizona
    -0.61
     Audiodateien
    -0.55
    Parcelize
    -0.55
     harmonics
    -0.54
    urlencoded
    -0.54
    unz
    -0.54
    Incompatible
    -0.53
    jointe
    -0.53
     الحره
    -0.53
     crdi
    -0.53
    POSITIVE LOGITS
     offset
    0.86
    offset
    0.84
     Offset
    0.75
     mean
    0.75
    Offset
    0.72
    OFFSET
    0.68
     shift
    0.66
     OFFSET
    0.66
    mean
    0.66
     offsets
    0.63
    Activations Density 3.079%

    No Known Activations