© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4398
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to something being shown or proven to be useful or effective

    oai_token-act-pair · gemini-2.0-flash

    prove

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    MethodManager
    -0.84
    contentLoaded
    -0.72
    الإنجليزية
    -0.71
     olympique
    -0.71
     AssemblyVersion
    -0.70
     noDo
    -0.68
    FieldBuilder
    -0.68
     ©️
    -0.65
     INCLUD
    -0.64
    Tikang
    -0.64
    POSITIVE LOGITS
     becoming
    0.49
    odom
    0.46
     nakalista
    0.42
    Becoming
    0.41
     obst
    0.41
    (&_
    0.41
     He
    0.40
     đối
    0.40
    becoming
    0.40
     organizing
    0.40
    Activations Density 0.958%

    No Known Activations