© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4060
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases which would fit into a variety of different topics and which appear frequently in corpora.

    oai_token-act-pair · gemini-2.0-flash

    Textual content

    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
    νε
    -0.42
    alade
    -0.41
    helle
    -0.38
     ∙
    -0.38
    ashqai
    -0.38
     glade
    -0.37
    entle
    -0.36
     cor
    -0.36
    lict
    -0.36
    >>>
    -0.36
    POSITIVE LOGITS
    +#+#
    1.20
     this
    1.16
     it
    1.08
     nakalista
    0.98
    this
    0.96
    ConstraintMaker
    0.94
     это
    0.93
     nó
    0.90
     kaynağından
    0.90
     этот
    0.88
    Activations Density 1.723%

    No Known Activations