© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15077
    Prev
    Next
    INDEX
    Explanations

    strings containing "vs" or "ve" often associated with coding or version numbers

    oai_token-act-pair · gemini-2.0-flash

    vs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    esgue
    -0.63
    IAB
    -0.59
    dientemente
    -0.59
    IsMutable
    -0.59
    numerusform
    -0.59
    AxisAlignment
    -0.57
     EconPapers
    -0.56
    TestingModule
    -0.56
    MLLoader
    -0.56
    RefNanny
    -0.55
    POSITIVE LOGITS
     V
    1.50
    V
    1.37
     VI
    0.92
     VB
    0.87
    Vt
    0.87
     Vane
    0.87
    VD
    0.85
     Vl
    0.84
    Vx
    0.83
    VB
    0.82
    Activations Density 1.333%

    No Known Activations