© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14322
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" at the beginning of a clause

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    FormBuilder
    -0.56
    HTTPResponse
    -0.48
    っこう
    -0.46
    __*/
    -0.45
    OOTD
    -0.45
    Abit
    -0.44
     Sum
    -0.44
    дова
    -0.43
     mala
    -0.43
    Sum
    -0.43
    POSITIVE LOGITS
    atorship
    0.62
     InputDecoration
    0.60
     jotka
    0.59
    >>()
    0.59
    ppincott
    0.57
    ziell
    0.56
    addContainerGap
    0.55
     Perseus
    0.53
    Gizmos
    0.53
    EndContext
    0.53
    Activations Density 0.229%

    No Known Activations