© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2199
    Prev
    Next
    INDEX
    Explanations

    words and numbers related to financial reports and time periods

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or code-related terms

    np_token-act-pair-logits · gpt-4o-mini

    financial reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    CppMethod
    -0.52
    ]=>
    -0.52
    ség
    -0.48
    FirstResponder
    -0.48
    rigkeit
    -0.48
    errHandler
    -0.47
    的目光
    -0.46
    жели
    -0.46
     promotion
    -0.46
     Posi
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.66
    SequentialGroup
    0.65
    ResumeLayout
    0.65
    KURZBESCHREIBUNG
    0.55
    oredCriteria
    0.53
    BASEPATH
    0.52
    stalk
    0.50
     resolves
    0.50
    DebuggerNonUser
    0.49
    易
    0.49
    Activations Density 1.497%

    No Known Activations