© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12490
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names and surrounding punctuation and adjectives like great and very which typically signify a positive sentiment towards the preceding noun.

    oai_token-act-pair · gemini-2.0-flash

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    UIControlState
    -0.59
     SEDS
    -0.58
     BoxFit
    -0.58
    NullException
    -0.57
    lorette
    -0.54
    Filmography
    -0.54
    twimg
    -0.51
     telefonisch
    -0.51
    nezeu
    -0.50
    cyjna
    -0.50
    POSITIVE LOGITS
    <bos>
    0.83
     estekak
    0.53
    //
    0.48
    ⓧ
    0.46
    RunWith
    0.44
     Reverso
    0.43
     estimés
    0.42
     jesu
    0.41
     autorytatywna
    0.41
    denly
    0.40
    Activations Density 9.269%

    No Known Activations