© 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. 13823
    Prev
    Next
    INDEX
    Explanations

    phrases about computers and personal opinions

    oai_token-act-pair · gemini-2.0-flash

    technical/computer contexts

    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
    省市镇
    -0.74
     wireType
    -0.74
    borderSide
    -0.73
    ^(@)
    -0.73
    ovico
    -0.71
    odenal
    -0.70
     Rhodes
    -0.70
    {}
    -0.68
     محفوظة
    -0.68
    　『
    -0.68
    POSITIVE LOGITS
    kloped
    0.55
    PreExecute
    0.43
     XCTest
    0.42
     burbu
    0.41
     úl
    0.40
     endwhile
    0.37
     câte
    0.36
     mijne
    0.36
     påver
    0.35
     engraçadas
    0.35
    Activations Density 3.503%

    No Known Activations