© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4401
    Prev
    Next
    INDEX
    Explanations

    seemingly random punctuation, conjunctions, and words related to creative pursuits or emotional states.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     those
    -0.56
     couv
    -0.55
     setuptools
    -0.54
     BoxFit
    -0.54
    AutoScaleMode
    -0.52
    xhr
    -0.51
     FontFamily
    -0.51
     Spisak
    -0.50
     Paleozoic
    -0.49
    หลัก
    -0.49
    POSITIVE LOGITS
    TagMode
    0.74
     فريبيس
    0.58
     متحده
    0.49
    pernicus
    0.48
    chequer
    0.46
     مرئيه
    0.44
     Deum
    0.44
    OGND
    0.44
    disambiguation
    0.43
    daq
    0.43
    Activations Density 1.633%

    No Known Activations