© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1609
    Prev
    Next
    INDEX
    Explanations

    punctuation marks preceded and followed by common words

    oai_token-act-pair · gemini-2.0-flash

    no

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     pescoço
    -0.49
    답
    -0.48
    aski
    -0.46
    êques
    -0.44
     disambiguazione
    -0.44
    rasz
    -0.44
    skapet
    -0.44
    tión
    -0.44
     Bakar
    -0.43
    oksi
    -0.43
    POSITIVE LOGITS
     no
    2.53
    no
    1.84
    No
    1.70
     No
    1.66
     NO
    1.63
    NO
    1.41
     kein
    1.08
     nessun
    1.05
     keine
    1.00
    Kein
    0.97
    Activations Density 2.068%

    No Known Activations