© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16023
    Prev
    Next
    INDEX
    Explanations

    quotes and reported speech

    oai_token-act-pair · gemini-2.0-flash

    speech

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ViewChild
    -0.58
     ModelExpression
    -0.57
    ernalia
    -0.55
     positive
    -0.51
     useAppContext
    -0.51
    InjectAttribute
    -0.50
    Controllo
    -0.50
     versa
    -0.49
    Positive
    -0.47
    istoitu
    -0.47
    POSITIVE LOGITS
    reactstrap
    0.63
    enumii
    0.56
     craindre
    0.55
    DebuggerNonUser
    0.54
    Appellants
    0.50
    konomi
    0.49
     vectorielles
    0.49
     rekening
    0.49
     mourir
    0.49
     quæ
    0.49
    Activations Density 6.882%

    No Known Activations