© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14838
    Prev
    Next
    INDEX
    Explanations

    sentences explaining something, using words like "because" and "that"

    oai_token-act-pair · gemini-2.0-flash

    Explanations

    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
    PullParser
    -0.60
    +};
    -0.60
     Offisielt
    -0.58
    TableAdapter
    -0.57
    numerusform
    -0.56
     Rangel
    -0.53
     unincorporated
    -0.52
    ReusableCell
    -0.52
    SOUNDBITE
    -0.51
     ſever
    -0.51
    POSITIVE LOGITS
     poveznice
    0.60
    endphp
    0.59
    abank
    0.52
     noDo
    0.49
    Infof
    0.48
    FunctionFlags
    0.47
    rungsseite
    0.47
    didSet
    0.47
     identi
    0.46
     enää
    0.46
    Activations Density 8.636%

    No Known Activations