© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13049
    Prev
    Next
    INDEX
    Explanations

    phrases like "is a" and "is the" followed by a person's occupation

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     дописавши
    -0.63
    openConnection
    -0.59
    RTSC
    -0.53
    BASEPATH
    -0.51
    İstinadlar
    -0.49
    NamedQueries
    -0.47
    deniz
    -0.46
    SizeF
    -0.44
     NSCoder
    -0.43
    خصة
    -0.43
    POSITIVE LOGITS
    NUMX
    0.58
    aturan
    0.56
    atko
    0.54
    WithIOException
    0.53
    udios
    0.53
    ovna
    0.52
    bibfield
    0.52
    RegistryLite
    0.50
    sprogram
    0.50
    maksud
    0.50
    Activations Density 1.333%

    No Known Activations