© 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. 9679
    Prev
    Next
    INDEX
    Explanations

    the tokens "C", "T", "s", "u", "r", "i", "l", and sometimes "k" combined, especially when combined with a period

    oai_token-act-pair · gemini-2.0-flash

    ins

    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
     PyTuple
    -0.51
     resourceCulture
    -0.50
    ieszka
    -0.50
    weile
    -0.49
    contentLoaded
    -0.47
     ProtoMessage
    -0.47
     decision
    -0.46
    ttes
    -0.45
    Viitteet
    -0.45
    通販
    -0.45
    POSITIVE LOGITS
    principalColumn
    0.74
    SequentialGroup
    0.61
     moun
    0.59
    ValueStyle
    0.58
    \{\\
    0.57
    NameInMap
    0.55
    +#+#
    0.55
    ########.
    0.54
    цездатний
    0.53
    RectangleBorder
    0.52
    Activations Density 0.751%

    No Known Activations